gigio-write-plan
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill constructs plan files using information from potentially untrusted sources such as PROJECT.md and user conversation content. These generated plans contain instructions and shell commands for subsequent agent sessions.
- Ingestion points: Data is ingested from PROJECT.md and direct user input during the planning phase.
- Boundary markers: The skill lacks explicit delimiters or instructions to prevent the agent from following malicious commands embedded within user-provided task descriptions or project goals.
- Capability inventory: The skill writes markdown files to the local .plans/ directory.
- Sanitization: There is no evidence of filtering or validation for the content placed in the check or acceptance fields of the generated plan.
Audit Metadata