SKILLEMALL.ai
RU Sign in

BC credential-manager

MANDATORY security foundation for OpenClaw. Consolidate scattered API keys and credentials into a secure .env file with proper permissions. Includes GPG encryption for high-value secrets, credential rotation tracking, deep scanning, and backup hardening. Use when setting up OpenClaw, migrating credentials, auditing security, or enforcing the .env standard. This is not optional — centralized credential management is a core requirement for secure OpenClaw deployments.

ClawHub Agent Skills author: TeeClaw v2.0.0 16 files · 1 script body ≈ 5 717 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 58/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency

IntegrationInfrastructureSecuritytype 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
B
85/100
safety, quality, tests
Safety 60%
89
Quality 40%
78
Run on models
none yet
Process rating
C
58/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
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

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 7

✓ No critical or high findings

Medium and low: 7
  • medium Risky intent intent-wallet-secrets CHANGELOG.md:118
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    4. Wallet private key sitting in plaintext `.env`
  • low Exfiltration read-dotenv CONSOLIDATION-RULE.md:84
    Reads a .env file (documentation of a security skill)
    source ~/.openclaw/.env
    security skill
  • low Exfiltration read-dotenv references/security.md:109
    Reads a .env file (documentation of a security skill)
    set -a && source ~/.openclaw/.env && set +a
    security skill
  • low Risky intent intent-wallet-secrets scripts/scan.py:56
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
    (r'(?:mnemonic|seed)\s*[=:]\s*["\'](?:\w+\s+){11,23}\w+', 'Possible mnemonic/seed phrase'),
    detector
  • low Risky intent intent-wallet-secrets scripts/validate.py:139
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    f"Line {line_num}: {key} looks like a mnemonic seed phrase ({len(words)} words). "
    quoted
  • low Exfiltration read-dotenv SKILL.md:705
    Reads a .env file (documentation of a security skill)
    source ~/.openclaw/.env
    security skill
  • low Exfiltration read-dotenv SKILL.md:735
    Reads a .env file (documentation of a security skill)
    source ~/.openclaw/.env
    security skill

Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5717 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 58/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (credential-manager) differs from the folder (openclaw-credential-manager)
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 5717 tokens
  • 100Steps. 103 steps
  • 100Failures and branches. 3 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 19 top-level sections: this looks like several domains in one skill

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)
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -232 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 470: enough signal without eating the budget
  • +4Structure: 51 headings
  • +3Step-by-step instructions: 103 items
  • +3Output format is stated explicitly
  • +4Has examples (47 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +3All 8 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
This credential-security skill is mostly coherent, but it needs review because it broadly scans and centralizes secrets while recommending unsafe passphrase and GPG handling patterns.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026