implement
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from project documentation, specifications, and tickets to guide code implementation and verification.
- Ingestion points: Reads from files in the
.agents/projects/<project>/directory, includingCONTEXT.md,LINKS.md,todo.md, approved specs, and ticket drafts. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as data rather than instructions.
- Capability inventory: The skill allows for source code modification, execution of local test suites and coverage tools, and posting comments to external platforms like Jira or GitHub.
- Sanitization: The instructions do not include steps for sanitizing or validating the content of the ingested project artifacts before they influence the implementation process.
Audit Metadata