developer-audience-context
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is instructed to ingest and process data from untrusted sources, including local codebase files (README.md, package.json, index.html) and external content (GitHub Issues, blog posts).\n- Ingestion points: Context is gathered from the local filesystem and suggested external developer community resources.\n- Boundary markers: The prompt instructions do not define delimiters or specific 'ignore embedded instructions' markers for the data being read.\n- Capability inventory: The skill is restricted to reading files and writing a markdown document; it does not perform command execution, network requests, or dynamic code loading.\n- Sanitization: No explicit sanitization or validation of the ingested content is performed.
Audit Metadata