skills/opencue/skills/skill-simplify/Gen Agent Trust Hub

skill-simplify

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes basic Bash shell commands (wc, cp, test, rm) for file metadata collection, backup creation, and restoration. These commands are executed locally on the user-specified target file.
  • [PROMPT_INJECTION]: The skill processes untrusted markdown content during refactoring, which represents a surface for indirect prompt injection. This risk is mitigated by explicit instructions to treat code blocks as data for classification rather than executable instructions, and the skill specifically excludes the execution of the files it modifies.
  • [EXTERNAL_DOWNLOADS]: No external network requests, script downloads, or package installations are performed by this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 12:39 PM
Security Audit — agent-trust-hub — skill-simplify