BC Security Scanner
Scan AI agent skills for security vulnerabilities, dangerous code patterns, and undeclared permissions. Three-layer analysis: dependency CVE scanning, static code analysis, and permission auditing. Returns structured JSON risk report. Use when the user asks to scan a skill for security issues, check for vulnerabilities, audit permissions, or assess skill safety.
As a process C 59/100 · Has gaps — weak spots: failures and branches, consistency, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 5417 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 59/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 16 mutating operations with no state check
- 40Consistency. Frontmatter name (Security Scanner) differs from the folder (security-scanner-plus)
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5417 tokens
- 100Steps. 63 steps
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 top-level sections: this looks like several domains in one skill
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 366: enough signal without eating the budget
- +4Structure: 43 headings
- +3Step-by-step instructions: 63 items
- +3Output format is stated explicitly
- +4Has examples (19 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.