cali-coding-codebase-spec

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard shell commands like unzip, find, and grep to perform reconnaissance on provided codebases. These operations are restricted to temporary and user-data directories.
  • [PROMPT_INJECTION]: As the skill's primary function is to interpret and document untrusted external source code, it possesses a surface for indirect prompt injection where instructions hidden in the code could attempt to bias the agent's output.
  • Ingestion points: External source code provided via ZIP archives, file uploads, or local paths (referenced in Phase 0).
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used to separate user-provided code from the agent's internal analysis logic.
  • Capability inventory: The skill utilizes file system tools (unzip, cat, find) and metadata generation capabilities within the agent's environment.
  • Sanitization: The instructions do not specify any validation or sanitization steps for the input code before it is read and processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 10:48 AM
Security Audit — agent-trust-hub — cali-coding-codebase-spec