skills/lev-os/agents/rp-review-cli/Gen Agent Trust Hub

rp-review-cli

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates within the expected scope of a code review tool, using authorized CLI commands to interact with the local repository context.\n- [COMMAND_EXECUTION]: The skill utilizes rp-cli to execute git and filesystem operations essential for surveying changes and analyzing code structure. This is the intended operation of the CLI-based workflow.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it processes untrusted code and git metadata.\n
  • Ingestion points: Reads repository content and history through commands like git diff, git log, and rp-cli read.\n
  • Boundary markers: Uses XML-style tags (<task>, <context>, <discovery_agent-guidelines>) within CLI command arguments to structure instructions.\n
  • Capability inventory: Possesses the ability to modify the filesystem via apply_edits and file_actions subcommands of rp-cli.\n
  • Sanitization: No explicit sanitization or escaping of repository-sourced data is documented before it is passed to the context builder.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 04:36 AM
Security Audit — agent-trust-hub — rp-review-cli