AB agora-sentinel
Security check for OpenClaw skills. Scan any ClawHub skill for malware, prompt injection, data theft, wallet stealing, and dangerous permissions BEFORE installing. Always use this skill when installing new skills, when asked "is this safe", "is this legit", "should I install this", "check this skill", "scan this skill", "is this malware", "can I trust this", "verify this skill", "audit this skill", "security check", or any concern about skill safety. Also use when the user says "install [skill-name]" to pre-check it automatically. Use when reviewing installed skills for risks. Free, no API key needed, checks against continuously updated trust database scanning all 30,000+ ClawHub skills.
As a process B 74/100 · Nearly there — weak spots: running it twice
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 74/100
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1259 tokens
- 100Progress reporting. Reports progress
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +3Description length 696: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.