SKILLEMALL.ai
GitHub ↗ RU Sign in

BC skill-risk-auditor

Comprehensive pre-install guard that audits third-party skills across nine risk areas — covering semantic integrity, supply chain, secrets, data exfiltration, injection resistance, permission scope, destructive potential, resource abuse, and persistence — with clear severity levels and plain-language explanations so users can make informed decisions.

ClawHub Agent Skills author: Xiaofang Yang v1.0.1 MIT-0 2 files body ≈ 8 561 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 55/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, execution cost

AnalyzerInfrastructuretype 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
82/100
safety, quality, tests
Safety 60%
93
Quality 40%
65
Run on models
none yet
Process rating
C
55/100
Has gaps
Inputs and preconditions w 11
0
When it triggers w 12
20
Running it twice w 4
30
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.

Instruction override 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Instruction override en-ignore-previous SKILL.md:245
    Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)
    - Force flags (`--force`, `-f`, `--no-preserve-root`) that bypass safety prompts
    security skill
  • low Risky intent intent-offensive-security SKILL.md:113
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Critical   | Hardcoded secrets in the skill itself; reads credentials and passes them to external services; accesses multiple credential stores beyond its stated purpose; or credential harvesting pa
  • low Risky intent intent-offensive-security SKILL.md:221
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Privilege escalation:**

Files scanned: 2. 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")
  • warning body-long SKILL.md body ≈ 8561 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 55/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 24 mutating operations with no state check
  • 40Execution cost. Instruction body is 8561 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 86 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 352: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 86 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: clean
This is a documentation-only skill that helps an agent review other skills before installation and does not contain code, install hooks, persistence, credential use, or network behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026