planning-spec
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill provides guidelines for structured planning and does not include any executable code, network operations, or persistence mechanisms.- [PROMPT_INJECTION]: The skill instructs agents to gather context from project documentation (e.g., AGENTS.md, docs/adr). This presents a surface for indirect prompt injection. Ingestion points: Project documentation files (AGENTS.md, CONTRIBUTING.md, decisions/); Boundary markers: None; Capability inventory: File system read access; Sanitization: None. This surface is inherent to context-aware agents and is mitigated by the skill's mandatory human-in-the-loop approval step.
Audit Metadata