CC torch-liquidation-bot

Autonomous vault-based liquidation keeper for Torch Market lending on Solana. Scans all migrated tokens for underwater loan positions using the SDK's bulk loan scanner (getAllLoanPositions), builds and executes liquidation transactions through a Torch Vault, and collects a 10% collateral bonus.

ClawHub Agent Skills author: mr brightside v10.7.1 MIT-0 36 files body ≈ 2 209 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

Integration Infrastructuretype and topics are labelled automatically from the skill text

Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode

JSON

Technical rating

71/100

safety, quality, tests

Safety 60%: 71
Quality 40%: 72
Run on models: none yet

Process rating

51/100

Has gaps

Result and completion w 14: 0
Inputs and preconditions w 11: 0
When it triggers w 12: 20

the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Risky intent medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

How to improve

Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.

For the model run — optional

Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 25

✓ No critical or high findings

Medium and low: 25

medium Risky intent intent-wallet-secrets SKILL.md:301

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
1. Never ask for a private key or seed phrase.
```
low Secrets in code secret-high-entropy-token agent.json:97

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"program_id": "8hbU…BeT",
```
quoted
low Secrets in code secret-high-entropy-token agent.json:185

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"wallet": "8cpW…nMa",
```
quoted
low Secrets in code secret-high-entropy-token agent.json:186

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"pda": "2rNk…Mmb",
```
detector
low Secrets in code secret-high-entropy-token audit_program.md:18

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
Program ID: `8hbU…BeT`
```
quoted
low Secrets in code secret-high-entropy-token audit_program.md:1041

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
3. **Transactions are deterministic.** Built from the Anchor IDL against the on-chain program. All accounts are PDA-derived. Verify the program ID (`8hbU…BeT`) if y
```
quoted
low Secrets in code secret-high-entropy-token audit_sdk.md:6

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
**On-Chain Program:** `8hbU…BeT` (V10.2.6 — unchanged)
```
quoted

low Secrets in code secret-high-entropy-token audit_sdk.md:484

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)

31. **V4.1.0 VersionedTransaction + Quote-Driven Trading** — Major SDK improvement, no on-chain program changes. All transaction builders now return `VersionedTransaction` (v0 messages) instead of leg

quoted

low Secrets in code secret-high-entropy-token audit_sdk.md:517

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
**On-Chain Version:** V10.2.6 (Program ID: `8hbU…BeT`) — unchanged from v10.2.6 audit
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:6

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
exports.PROGRAM_ID = new web3…Key('8hbU…BeT');
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:8

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
exports.WSOL_MINT = new web3…Key('So11…112');
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:10

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
exports.MEMO_PROGRAM_ID = new web3…Key('Memo…cHr');
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:12

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
expo…_ID = new web3…Key('Toke…uEb');
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:36

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'6JkG…htm', // legacy SPL test token (pre-prod-beta)
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/tokens.js:397

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
programId === 'Memo…cHr' ||
```
detector
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:2

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "8hbU…BeT",
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:471

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "ATok…knL"
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:864

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "ATok…knL"
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:872

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "Sysv…111"
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:1211

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "ATok…knL"
```
quoted
low Secrets in code secret-high-entropy-token SKILL.md:78

High-entropy token-like string (may be an id, hash or a credential)
```
program-id: 8hbU…BeT
```
low Secrets in code secret-high-entropy-token SKILL.md:291

High-entropy token-like string (may be an id, hash or a credential)
```
PROGRAM_ID      8hbU…BeT
```
low Secrets in code secret-high-entropy-token SKILL.md:329

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- Program: `8hbU…BeT`
```
quoted
low Risky intent intent-offensive-security verification.md:267

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
| **CPI safety** | Reentrancy via Raydium CPIs, privilege escalation | Cross-program invocation is outside arithmetic scope |
```
low Risky intent intent-offensive-security verification.md:278

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
3. **CPI safety** -- can Raydium CPIs be exploited for reentrancy or privilege escalation?
```

Files scanned: 36. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

warning description-no-when description does not say WHEN to use the skill (no "use when")
note frontmatter-key unknown frontmatter key "requires"

Process rating: all ten parameters 51/100

0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
20When it triggers. No condition that starts the skill
30Running it twice. 2 mutating operations with no state check
40Consistency. Frontmatter name (torch-liquidation-bot) differs from the folder (torchliquidationbot)
60Tools and files. Uses tools (web) that frontmatter does not declare
100Steps. 8 steps
100Failures and branches. 3 branches, has a failure section
100Execution cost. Instruction body is 2209 tokens
100Progress reporting. Reports progress

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

+5Description has no quoted example phrases that should trigger the skill
+4Description does not say when NOT to use the skill (false activations)
+3Output format is not stated: the model decides each time
+2Single-language instructions
+3Description length 295: enough signal without eating the budget
+4Structure: 16 headings
+3Step-by-step instructions: 8 items
+4Has examples (8 code blocks)
+1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.

External checks

ClawHub: suspicious

The liquidation bot is mostly transparent about running live financial transactions, but its install path and bundled SDK expose broader financial powers than the stated keeper role.

LLM: suspicious (high) · VirusTotal: benign · 10 Sept 2026

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 36

agent.json 8K
audit_program.md 87K
audit_sdk.md 59K
lib/kit/config.d.ts 0K
lib/kit/config.js 3K
lib/kit/constants.d.ts 0K
lib/kit/constants.js 0K
lib/kit/index.d.ts 0K
lib/kit/index.js 10K
lib/kit/types.d.ts 1K
lib/kit/types.js 0K
lib/kit/utils.d.ts 1K
lib/kit/utils.js 2K
lib/torchsdk/constants.d.ts 1K
lib/torchsdk/constants.js 6K
lib/torchsdk/ephemeral.d.ts 0K
lib/torchsdk/ephemeral.js 1K
lib/torchsdk/index.d.ts 3K
lib/torchsdk/index.js 12K
lib/torchsdk/program.d.ts 7K
lib/torchsdk/program.js 12K
lib/torchsdk/quotes.d.ts 1K
lib/torchsdk/quotes.js 9K
lib/torchsdk/said.d.ts 1K
lib/torchsdk/said.js 3K
lib/torchsdk/tokens.d.ts 4K
lib/torchsdk/tokens.js 49K
lib/torchsdk/torch_market.json 153K
lib/torchsdk/transactions.d.ts 13K
lib/torchsdk/transactions.js 85K
lib/torchsdk/types.d.ts 16K
lib/torchsdk/types.js 0K
risk.md 22K
skill-card.md 3K
SKILL.md 13K
verification.md 27K

Frontmatter

version: 10.7.1

license: MIT

disable-model-invocation: true

requires: {"env":[{"name":"SOLANA_RPC_URL","required":true},{"name":"VAULT_CREATOR","required":true},{"name":"SOLANA_PRIVATE_KEY",

metadata: {"clawdbot":{"requires":{"env":[{"name":"SOLANA_RPC_URL","required":true},{"name":"VAULT_CREATOR","required":true},{"nam

compatibility: REQUIRED: SOLANA_RPC_URL (HTTPS Solana RPC endpoint). REQUIRED: VAULT_CREATOR (vault creator pubkey). OPTIONAL: SOLANA_P

Dates

In catalog since 9 Feb 2026

Updated in catalog 11 May 2026

First seen here 10 Sept 2026

Last analysis 11 Sept 2026, 02:49 UTC

Last seen in crawl 10 h ago

Score history

Date		Score	Safety	Qual.
10 Sept 2026	C	71	71	72

Similar skills

C torch-liquidation-bot LeoYeAI/openclaw-master-skills
C torch-liquidation-bot modbender/skill-library-mcp