breakdown-plan

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a specialized instruction set and template collection for senior project managers. It does not contain any executable scripts, network exfiltration logic, or requests for sensitive data access.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it is designed to ingest project artifacts like PRDs and technical breakdowns to generate its output.\n
  • Ingestion points: Files located in the project's /docs/ways-of-work/plan/ directory as described in SKILL.md.\n
  • Boundary markers: None; the instructions do not specify the use of delimiters or warnings to ignore embedded instructions in the source documents.\n
  • Capability inventory: The skill focuses on documentation generation and issue formatting; it does not request high-privilege tool execution or external network operations.\n
  • Sanitization: None; the skill processes project artifacts as they are provided in the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 12:20 AM
Security Audit — agent-trust-hub — breakdown-plan