executing-plans

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection through external plan ingestion.
  • Ingestion points: Step 1 in SKILL.md directs the agent to read an external plan file.
  • Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions within the plan that contradict safety rules.
  • Capability inventory: The skill is used for development tasks, which typically imply file system modification and command execution capabilities.
  • Sanitization: Absent; the skill directs the agent to 'follow each step exactly' without prior validation or sanitization of the plan's content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:17 PM