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

rp-build-cli

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for a specialized CLI-based development workflow. No malicious behavior such as obfuscation, credential theft, or unauthorized network activity was detected.
  • [COMMAND_EXECUTION]: The skill relies on executing rp-cli shell commands to interact with the codebase. Evidence: Commands include tree, search, read, and apply_edits executed via rp-cli -e. Context: These operations are scoped to the development workspace and are necessary for the skill's core functionality of assisting with code changes.
  • [PROMPT_INJECTION]: As a coding assistant, the skill has an inherent surface for indirect prompt injection because it processes content from the local codebase. Ingestion points: Files read via rp-cli -e 'read ...'. Boundary markers: None explicitly defined in the workflow instructions. Capability inventory: Includes the ability to create and modify files in the repository. Sanitization: No specific sanitization or escaping of file content is described. This is a standard risk for development-oriented agents and is mitigated by the user's control over the codebase being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:48 PM
Security Audit — agent-trust-hub — rp-build-cli