BC security-scan
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions. Use when auditing a .claude/ directory — CLAUDE.md, settings.json, MCP servers, hooks, or agent definitions.
This skill scans Claude Code configuration for vulnerabilities using AgentShield—checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions. Promises to catch injection attacks and misconfigurations.
Verification shows no critical or high-risk findings, one medium or low issue. Safety score 99, quality 87, but process score only 57—the checking logic lacks confidence. Never ran on actual models. Single file, no scripts, 1046 tokens total.
Works for quick config audits. If you need serious injection-attack protection in production, the process score is a red flag. Install if you're scanning your own configs for compliance, skip if you expect reliable threat detection.
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks…
As a process C 57/100 · Has gaps — weak spots: when it triggers, failures and branches, 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
-
low Risky intent
intent-offensive-securitySKILL.md:102Offensive-security / dual-use content (legitimate for authorised testing; review intended use)1. **Attacker (Red Team)** — finds attack vectors
Files scanned: 1. 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 57/100
- 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
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 28 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1046 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)
- +1No license
- +2Single-language instructions
- +3Description length 329: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 28 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.