rp-investigate-cli

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill frequently uses shell commands via the rp-cli utility to manage workspace windows, read file systems, and execute repository actions. This includes the ability to modify the codebase through the apply_edits and file_actions tools.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes data from the target codebase and passes it to secondary analysis tools.
  • Ingestion points: Data is ingested from the repository through commands like read_file, file_search, and the automated scanning performed by the builder command.
  • Boundary markers: The instructions do not define specific delimiters or markers to prevent the agent or the secondary analysis tools from inadvertently executing instructions embedded within the codebase files.
  • Capability inventory: The skill possesses the ability to perform high-privilege operations such as modifying files and creating new repository items.
  • Sanitization: No content validation or sanitization process is described for the data retrieved from the repository before it is used in deep analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:48 PM
Security Audit — agent-trust-hub — rp-investigate-cli