state-map
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The generated HTML visualization fetches d3.js from Cloudflare's CDN and fonts from Google Fonts. Both are well-known and trusted service providers.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core function of processing untrusted source code.
- Ingestion points: Subagents analyze the target repository code and user-provided specifications as described in SKILL.md.
- Boundary markers: The skill does not explicitly use delimiters or instructions to ignore potentially malicious content within the analyzed files.
- Capability inventory: The skill executes scripts/build.py which has the capability to write files (Path.write_text) to the local system.
- Sanitization: Sanitization is present via json.dumps and manual character replacement in build.py, as well as a JavaScript escaping function in the HTML template.
Audit Metadata