SKILLEMALL.ai

BC jcvd

Authorization gatekeeper for OpenClaw agents. Scoped grants, time-bound permissions, skill scanning, prompt injection detection, and full audit trail. The roundhouse kick your agent needs.

ClawHub Agent Skills author: Juan Figuera v0.1.0 MIT-0 6 files · 2 scripts body ≈ 2 427 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process C 56/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
94
Quality 40%
74
Run on models
none yet
Process rating
C
56/100
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

How to improve

  1. 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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Risky intent intent-offensive-security README.md:67
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Privilege escalation vectors
  • low Dangerous commands cmd-privilege scan-skill.sh:146
    Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
    "chmod 777"
    code literalsecurity skill
  • low Risky intent intent-offensive-security SKILL.md:108
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    4. **Privilege escalation** -- Attempts to modify SOUL.md, IDENTITY.md, openclaw.json, or agent configuration
  • low Risky intent intent-offensive-security SKILL.md:129
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    [PASS|WARN|FAIL] Privilege escalation

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 6. 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 "homepage"

Process rating: all ten parameters 56/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 40Consistency. Frontmatter name (jcvd) differs from the folder (jean-claw-van-damme)
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 65Failures and branches. 3 branches
  • 100Steps. 83 steps
  • 100Execution cost. Instruction body is 2427 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 (3 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 188: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 83 items
  • +3Output format is stated explicitly
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: clean
This security skill is purpose-aligned and does not show exfiltration or destructive behavior, though users should understand its local audit logging and helper scripts before installing.
LLM: benign (high) · VirusTotal: · 29 May 2026