AB github-actions-self-hosted-risk-audit
Audit GitHub Actions workflows that use self-hosted runners for untrusted trigger and credential-hardening risks.
As a process B 70/100 · Nearly there — weak spots: when it triggers, failures and branches, progress reporting
How to improve
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 · 0
✓ No critical or high findings
Files scanned: 6. 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 70/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 465 tokens
- 100Running it twice. No mutating operations
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 113: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 5 headings
- +3Step-by-step instructions: 18 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.
External checks
ClawHub: clean
The scan shows a low-risk skill with no concrete evidence of hidden, destructive, or deceptive behavior; the main issue is missing explicit permission metadata.
LLM: benign (medium) · VirusTotal: · 29 May 2026