skills/udecode/plate/triage/Gen Agent Trust Hub

triage

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill directs the agent to switch models and adhere to specific behavioral constraints during execution. These instructions serve as operational guidelines for efficiency and do not represent malicious intent or attempts to bypass security filters.\n- [COMMAND_EXECUTION]: The workflow involves file system modifications, specifically renaming and deleting files in the todos/ directory based on user decisions. This is expected behavior for a triage application and does not involve the execution of arbitrary shell commands or external scripts.\n- [DATA_EXPOSURE]: The skill reads from the todos/ directory to present findings to the user. This data access is restricted to the specific local path required for the skill's intended functionality and does not involve exfiltration of sensitive information.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:53 AM