tdg-personal/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.
62
78%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill instructs running npx ecc-agentshield (which pulls and executes the package from https://www.npmjs.com/package/ecc-agentshield and its repo https://github.com/affaan-m/agentshield) at runtime, meaning external code is fetched and executed and is a required dependency for the skill.
Where we found it
ecc-agentshield
dependency · 13 sites
The plugin instructs the agent to run `npx ecc-agentshield` (and optionally `npm install -g ecc-agentshield`), which fetches and executes the external npm package ecc-agentshield from the npm registry at runtime.
affaan-m/agentshield@v1
dependency · 1 site
The plugin instructs users to add a GitHub Action `affaan-m/agentshield@v1` to their CI pipeline, which fetches and executes external code from a third-party GitHub repository.
SKILL.md
123
- uses: affaan-m/agentshield@v1
- Audited
- Security analysis