sp-executing-plans

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes instructions from external plan files, which constitutes an ingestion point for untrusted data that the agent is directed to follow.
  • Ingestion points: The agent reads a 'plan file' in the load and review phase (Step 1.2).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate plan content from agent instructions.
  • Capability inventory: The skill's workflow includes managing git worktrees, implementing code changes on the filesystem, and running verification tests.
  • Sanitization: No sanitization or validation of the plan file content is specified before execution begins.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:27 AM
Security Audit — agent-trust-hub — sp-executing-plans