principle-laziness-protocol
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or exfiltration vectors were identified. The skill defines architectural and coding style guidelines for minimizing complexity.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external files (pstack capability contract and adapters) to define tool usage, creating a data ingestion surface.
- Ingestion points: references/runtime.md references pstack/references/capability-contract.md and pstack/references/adapters/.
- Boundary markers: Absent.
- Capability inventory: Mentions verbs explore, implement, review, parallel, ask_user, verify, and model_role.
- Sanitization: Absent.
Audit Metadata