prd-to-plan
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized data exfiltration patterns were detected within the skill instructions.
- [COMMAND_EXECUTION]: The skill instructs the agent to explore the codebase to understand the existing architecture. This is a read-only context-gathering operation consistent with the skill's purpose.
- [PROMPT_INJECTION]: The skill is designed to process untrusted data from user-provided PRDs. 1. Ingestion points: User-pasted content or PRD files. 2. Boundary markers: Absent. 3. Capability inventory: Filesystem exploration and plan file creation. 4. Sanitization: Absent. While this presents a surface for indirect prompt injection, the risk is assessed as safe given the specific architectural mapping tasks required.
Audit Metadata