context-driven-development
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent is instructed to read and rely on project documentation artifacts.
- Ingestion points: The agent reads markdown files such as product.md and tech-stack.md from the local project directory.
- Boundary markers: There are no instructions provided to the agent to use delimiters or protective measures when processing these files.
- Capability inventory: The agent possesses file system read/write access and coordinates with other planning and execution agents.
- Sanitization: The skill does not include any steps for sanitizing or validating the content of the documentation files before processing.
Audit Metadata