Skills
Navigate
skills/schneidenbach/skills/revu/Gen Agent Trust Hub

revu

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes review comments from an external tool, which are then used as instructions to edit files.
  • Ingestion points: SKILL.md (Step 3, stdout of the revu command).
  • Boundary markers: Absent; tool output is processed directly as Markdown comments without dedicated delimiters.
  • Capability inventory: SKILL.md (Step 2 uses the bash tool for command execution; Step 3 involves file system modifications to address comments).
  • Sanitization: Instructions in SKILL.md (Step 4) require the agent to confirm destructive actions with the user before execution.
  • [COMMAND_EXECUTION]: The skill uses the bash tool to execute the revu CLI tool with background processing enabled to handle long-running review sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 03:21 AM