clarify-with-docs
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or unauthorized data exfiltration attempts were detected. The skill's primary function is to facilitate planning through human-in-the-loop clarification and documentation management.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests content from external sources such as tickets, epics, and codebase documentation. However, the potential impact is significantly mitigated because the skill's capabilities are limited to generating questions for a human-in-the-loop and updating local markdown files. There are no automated execution or exfiltration pathways.
- Ingestion points: Reads user-provided plans, tickets, and existing codebase/documentation (SKILL.md).
- Boundary markers: None explicitly defined to separate untrusted data from instructions.
- Capability inventory: Reads files for context; writes/updates CONTEXT.md and ADR files in the docs/ directory.
- Sanitization: None detected; the skill relies on the Human-In-The-Loop (HITL) process to validate the generated output.
Audit Metadata