icp-deploy-check

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the ripgrep (rg) command-line tool to perform static analysis of the local repository. These commands are restricted to read-only search operations on the source code to identify entrypoints and specific function calls.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted source code from external repositories. This presents an indirect prompt injection surface where malicious content (such as instructions hidden in code comments or strings) could attempt to influence the agent's logic or the resulting security report.\n
  • Ingestion points: Rust source files (.rs), frontend code, and agent client code within the target repository.\n
  • Boundary markers: The skill lacks explicit instructions for the agent to disregard instructions embedded within the data it is auditing.\n
  • Capability inventory: The agent generates a structured security report based on its findings; it does not execute the audited code or perform network operations.\n
  • Sanitization: No sanitization or escaping of the processed code content is specified in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 10:45 PM