CC Xena Protocol
Xena Protocol — scan your Gmail for phishing, crypto scams, impersonation, and BEC. Optionally submit hashed reports to an on-chain registry on Ethereum Sepolia so every other Xena user inherits your detections.
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, consistency
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
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.
- 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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Broad scope
meta-agent-memory-dumpHEARTBEAT.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensHEARTBEAT.md
-
medium Risky intent
intent-wallet-secretsREADME.md:137Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- Agent wallet private key lives in `~/.openclaw/phishing-detection/config.json`.
-
medium Risky intent
intent-wallet-secretsSKILL.md:67Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- `wallet_private_key`: the agent wallet private key (reporter mode only)
-
medium Risky intent
intent-wallet-secretsSKILL.md:326Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- Never share the wallet private key with the user (show address only).
-
low Risky intent
intent-wallet-secretsbin/registry_client.py:11Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)All transactions go through the on-disk agent wallet private key passed
quoted -
low Risky intent
intent-wallet-secretsbin/trainer.py:54Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)"Your Coinbase wallet will be frozen unless you verify ownership. Provide your seed phrase within the hour.",
quoted -
low Risky intent
intent-wallet-secretsbin/trainer.py:61Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)"Crypto airdrop: connect your wallet to receive 5000 free tokens. Enter your 12 word seed phrase to qualify.",
quoted -
low Secrets in code
secret-high-entropy-tokendata/deployed.json:2High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"address": "0xbD…5E2",
quoted
Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "activation"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (Xena Protocol) differs from the folder (xena-protocol)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 42 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Execution cost. Instruction body is 2996 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (14 tags): a typed call is more reliable
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
- +1No license
- +2Single-language instructions
- +3Description length 211: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.