gsd-plan-phase
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Potential for indirect prompt injection due to the ingestion of external untrusted data.
- Ingestion points: The skill accepts external files through the
--prdargument and reads from existingRESEARCH.mdandVERIFICATION.mdfiles in the environment (SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from obeying commands that might be embedded in the external documentation it processes.
- Capability inventory: The agent has access to powerful tools including
Bash,Write, andWebFetch, which could be exploited if malicious instructions are successfully injected via the processed files. - Sanitization: There is no evidence of sanitization, escaping, or validation of the contents of the PRD or research files before they are provided to the planning agent.
Audit Metadata