AD tommo-skill-guard
Security scanner for OpenClaw agent skills. Pre-install check via ClawHub page, local pattern scanning via read tool (zero exec), integrity verification. Use when: (1) installing a new skill — check first, (2) audit installed skills, (3) check if a skill is flagged on ClawHub, (4) scan for hardcoded secrets or dangerous patterns. Homepage: https://clawhub.ai/skills/tommo-skill-guard
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-privilegereferences/security-patterns.md:43Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)| `chmod 777` | Remove all permissions restrictions |
tablesecurity skill -
low Dangerous commands
cmd-disable-securityreferences/security-patterns.md:75Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation table row; documentation of a security skill)| `Set-ExecutionPolicy Bypass` | PowerShell |
tablesecurity skill -
low Dangerous commands
cmd-execpolicy-bypassreferences/security-patterns.md:75Runs PowerShell with execution policy bypassed (documentation table row; documentation of a security skill)| `Set-ExecutionPolicy Bypass` | PowerShell |
tablesecurity skill
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 43/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 914 tokens
- 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)
- +3Output format is not stated: the model decides each time
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 385: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.