plan-checker
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from local project files, creating an ingestion surface for potentially untrusted content.
- Ingestion points: The skill reads contents from
.gsd/ROADMAP.md,.gsd/REQUIREMENTS.md, and.gsd/phases/{N}/*-PLAN.mdduring the Load Context step. - Boundary markers: The instructions lack specific delimiters or instructions to the agent to disregard natural language commands that might be embedded within the project files.
- Capability inventory: The skill has no documented capabilities for system command execution, file writing, or network operations, which significantly mitigates the risk of prompt injection exploitation.
- Sanitization: There is no evidence of content sanitization or validation before the data is processed by the agent.
Audit Metadata