executing-plans

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides procedural guidance for software development workflows and does not contain any executable code or malicious commands.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) because it reads and executes instructions from external implementation plans.
  • Ingestion points: Step 1 (Read plan file).
  • Boundary markers: Absent; the skill does not use specific delimiters to isolate plan content.
  • Capability inventory: The skill enables the agent to perform task implementation and verification, which typically involves file system modifications and CLI command execution.
  • Sanitization: The skill includes a manual mitigation by requiring the agent to "review critically" and raise concerns with a human partner before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 03:34 PM