do-it
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a high-level instruction set for an agent to coordinate other specialized sub-skills. It does not perform direct file system access, network operations, or command execution itself.
- [INDIRECT_PROMPT_INJECTION]: The orchestrator has a natural attack surface for indirect injection as it passes user requests through a multi-step pipeline.
- Ingestion points: Takes an "explicit end-to-end ask" from the user in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in this layer.
- Capability inventory: Invokes child skills (
do-debug,do-plan,do-work,do-commit) that can perform file writes and Git operations. - Sanitization: No specific sanitization or filtering logic is defined for the input strings passed to child skills.
- Context: The risk is categorized as low because this is a coordination wrapper relying on the safety constraints of the child skills it executes.
Audit Metadata