internal-link-audit
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
scripts/check_internal_links.shto build the link graph and uses standard Node.js commands (npm run build,npm test) for site building and testing. These are appropriate for the tool's stated purpose of auditing a local web project. - [INDIRECT_PROMPT_INJECTION]: The skill reads and processes the content of HTML files in the
dist/directory and source files insrc/to identify links and suggest anchor text. This creates an attack surface where malicious instructions hidden in the site's content or metadata could influence the agent's behavior. - Ingestion points: The agent reads built HTML files from
dist/and source code fromsrc/pages/andsrc/config.ts. - Boundary markers: No specific delimiters or safety instructions are defined to separate the audited content from the agent's instructions.
- Capability inventory: The skill can modify source files (
src/pages/*.astro,src/config.ts) and execute shell commands (bash,npm). - Sanitization: There is no mention of sanitizing or filtering the content ingested from the audited files.
Audit Metadata