greenfield
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external file, creating a surface for potential prompt injection attacks.
- Ingestion points: The skill reads the BRIEF.md file from the project root to initiate the planning process as described in the Trigger section.
- Boundary markers: The instructions do not define delimiters or specific safety warnings to the AI when processing the brief content to prevent it from being interpreted as instructions.
- Capability inventory: The skill possesses file writing capabilities through the Write tool and the ability to spawn new sub-agents using the Agent tool, which could be misdirected if the brief contains malicious instructions.
- Sanitization: There is no evidence of sanitization or content validation for the data read from BRIEF.md before it is passed to the Research, Architect, PM, and Security agents.
Audit Metadata