executing-plans

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the execution of arbitrary steps from an external plan file, creating a surface for malicious instructions to influence agent behavior.
  • Ingestion points: The agent is instructed to read an external plan file in Step 1 as defined in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between plan data and core instructions.
  • Capability inventory: The skill involves implementation tasks that likely require command execution and file modifications, as well as git worktree usage for isolation (SKILL.md).
  • Sanitization: The skill contains no requirements for sanitizing or validating the plan file content before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:09 PM
Security Audit — agent-trust-hub — executing-plans