BC skill-audit-framework
Structured security and quality audit framework for AI agent skills. Teaches you what to check before installing any skill.
As a process C 52/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 Broad scope
meta-agent-memory-dumpMEMORY.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensMEMORY.md
-
low Risky intent
intent-offensive-securityMEMORY.md:16Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Credential harvesting**: Skills requesting unrelated API keys and exfiltrating them
-
low Dangerous commands
cmd-pipe-to-shellSKILL.md:87Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)- [ ] No `curl | bash` or `curl | python` install patterns
negated
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 52/100
- 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. 4 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
- 100Steps. 42 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1221 tokens
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 123: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.