reroute-plan
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill body and scripts confirms no malicious behavior. The skill operates exclusively on local project metadata and spec files.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests input from potentially untrusted sub-agents (discoveries), it mitigates exploitation through mandatory Phase 1 (Diagnosis) and Phase 2 (Classification) stops, which require explicit user approval before any file modifications or task rerouting occurs.
- [COMMAND_EXECUTION]: The skill uses a delegated sub-skill model for file edits and plan updates, avoiding direct shell execution of untrusted input.
Audit Metadata