setup-dev-and-contributing
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from existing repository files such as DEVELOPMENT.md, CONTRIBUTING.md, AGENTS.md, and CLAUDE.md to adapt templates to the specific repository context. This constitutes an attack surface where instructions embedded in local files could potentially influence agent behavior during scaffolding.\n
- Ingestion points: Existing documentation files (DEVELOPMENT.md, CONTRIBUTING.md, AGENTS.md, CLAUDE.md) and project configuration files (pyproject.toml, go.mod, etc.) within the target repository.\n
- Boundary markers: The skill does not specify the use of delimiters or specific safety instructions when reading existing repository content.\n
- Capability inventory: The skill is designed to write multiple markdown files to the local file system and modify agent entry-point files.\n
- Sanitization: There is no evidence of explicit content sanitization or validation for the data ingested from the repository files.
Audit Metadata