developer-audience-context
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes an 'Auto-Draft' feature that processes external, untrusted data from the user's codebase, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: The skill reads from
README.md,/docs,package.json,pyproject.toml, GitHub Issues, and blog posts to draft developer context. - Boundary markers: There are no explicit instructions to the agent to use delimiters or to ignore embedded commands within the analyzed files.
- Capability inventory: The skill is authorized to read local files and write the generated context to
.agents/developer-audience-context.md. - Sanitization: No explicit sanitization, validation, or escaping mechanisms for the ingested content are defined in the instructions.
Audit Metadata