gigio-execute-plan
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and execute instructions from external plan files and project context, which introduces a vulnerability to indirect prompt injection.
- Ingestion points: The skill reads project goals, existing grants, sources, and current work status from external files to guide its actions.
- Boundary markers: The instructions lack specific requirements for using delimiters or isolation markers to separate untrusted data in plans from the agent's core instructions.
- Capability inventory: The skill allows for a wide range of actions including analysis, implementation, file modification, and experiment execution.
- Sanitization: There are no instructions for sanitizing or validating the content of the plan files before the agent executes the contained tasks.
Audit Metadata