analyze-code

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the execution of project-intel.mjs, a local utility used for repository indexing and metadata extraction. This process involves shell commands that output results to the /tmp directory for further processing.
  • [EXTERNAL_DOWNLOADS]: The documentation references the use of Model Context Protocol (MCP) tools, specifically the @anthropic-ai/mcp-server-ref package, to verify library behaviors against official documentation.
  • [PROMPT_INJECTION]: As a tool designed to analyze external code, the skill possesses an indirect prompt injection surface. 1. Ingestion points: The skill reads local repository files and symbol metadata. 2. Boundary markers: The instructions do not specify the use of delimiters or specific warnings to isolate ingested content. 3. Capability inventory: The agent can execute local commands and access MCP tools. 4. Sanitization: No sanitization steps are defined for the code content retrieved from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 09:20 PM
Security Audit — agent-trust-hub — analyze-code