mission-recovery
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security threats were identified. The skill defines a specialized workflow for task recovery by scanning local metadata artifacts.
- [SAFE]: Indirect Prompt Injection Surface Evaluation:
- Ingestion points: The agent reads CSV files from
issues/and.mission/directories as part of the recovery process. - Boundary markers: The instructions do not specify explicit delimiters to separate task data from agent instructions.
- Capability inventory: The skill facilitates file reading, basic file modification (state updates), and delegation to a secondary task execution skill.
- Sanitization: The skill relies on structural schema validation but does not explicitly sanitize the text content of the fields. Given the intended use for local project management, the risk is minimal.
- [NO_CODE]: The skill consists entirely of instructional content in Markdown and does not contain any executable code, scripts, or external dependencies.
Audit Metadata