fmway-bugs
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted bug reports and project documentation, which constitutes a standard attack surface for indirect prompt injection.
- Ingestion points: The agent reads content from PRD.md, the docs/ directory, and requirement tickets (TICKET.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external documentation as data rather than instructions.
- Capability inventory: The skill utilizes shell command execution (git branch management, worktree creation, testing, and linting tools) and file system write operations (writing documentation and code fixes).
- Sanitization: The instructions do not specify input validation or sanitization routines for the data ingested during the discovery phase.
Audit Metadata