executing-plans
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill is entirely process-oriented.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and executing tasks from an external plan file.
- Ingestion points: Loading and reading the plan file in 'Step 1: Load and Review Plan'.
- Boundary markers: Absent; the skill does not specify delimiters or explicit instructions to ignore instructions embedded within the plan content.
- Capability inventory: The skill executes tasks which can involve any tools or scripts permitted by the agent's environment.
- Sanitization: Absent; the skill relies on the agent's 'critical review' and human partner feedback at batch checkpoints as the primary safety control.
Audit Metadata