repo-workflow-conventions
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines procedures for the agent to ingest and act upon repository-based content, creating a potential surface for instructions embedded in data to influence agent behavior.
- Ingestion points: The agent is instructed to read and process repository files including
*.md,*.local.md, and planning documents namedYYYY-MM-DD-<name>.mdto determine project conventions and tasks. - Boundary markers: The instructions do not specify the use of delimiters or clear separation markers when interpolating content from these repository files into the agent's context.
- Capability inventory: The skill grants the agent authority to perform file system operations (creation, movement, and deletion of markdown files) and Git repository management (creating branches, switching branches, and performing commits on user request).
- Sanitization: There are no explicit instructions for sanitizing or validating the content of repository files before they are processed by the agent's workflow logic.
Audit Metadata