BF skill-install-guardian
Inspect third-party Claude/OpenClaw/Codex/OpenCode skills, plugins, repos, npm packages, pip packages, shell installers, and GitHub Actions before any download or installation. Use automatically whenever a user asks to install, add, pull, clone, run, curl-bash, npm install, pip install, clawhub install, or use a skill/plugin from GitHub, ClawHub, or other registries. Perform source reputation checks first, then pre-download code review, then post-download deep inspection without executing install scripts. Block or escalate when you detect credential theft, data exfiltration, remote command execution, malicious IP/domain beacons, wallet theft, obfuscation, suspicious lifecycle hooks, prompt-injection-to-shell patterns, unknown packages, typosquatting, dependency confusion, or unsafe GitHub Actions/workflows.
Inspect third-party Claude/OpenClaw/Codex/OpenCode skills, plugins, repos, npm packages, pip packages, shell installers, and GitHub Actions before any…
As a process F 32/100 · Will not run — References files that are not bundled: scripts/*.ts
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 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
- The text references files that are not there: add them or drop the references.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Risky intent
intent-wallet-secretsfindings-catalog.md:21Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- Seed phrase capture or RPC signing interception
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/*.ts
Process rating: all ten parameters 32/100
- 0Tools and files. 1 referenced file(s) missing: scripts/*.ts
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-install-guardian) differs from the folder (security-audit-tools)
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4608 tokens
- 100Steps. 116 steps
- low 12 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)
- +3Description length 818: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -252 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 45 headings
- +3Step-by-step instructions: 116 items
- +4Has examples (45 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.