executing-plans
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions to override system prompts or bypass safety filters were found.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file access, or unauthorized network operations were detected.
- [Indirect Prompt Injection] (LOW): The skill reads and executes steps from external plan files. While this presents an ingestion surface for untrusted data, the instructions mandate critical review, human checkpoints, and explicit 'STOP' conditions for blockers, which are effective mitigations.
- [Command Execution] (SAFE): While the skill implies executing tasks, it does not contain hardcoded dangerous commands or shell scripts. It relies on the agent's existing capabilities to fulfill the plan steps.
- [External Downloads] (SAFE): No external package installations or remote script fetches were found. References to 'superpowers' skills appear to be internal workflow dependencies.
Audit Metadata