detect-static-dependencies

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution Considerations: The skill permits the use of command-line tools like rg -n, grep, or shell readers as fallback mechanisms when standard file-reading utilities fail.
  • Evidence: Located in the "Execution Contract" section of SKILL.md.
  • Context: The capability is constrained by a requirement to verify that the canonical path stays within the workspace and to stop immediately on any permission or workspace-boundary policy failure.
  • Indirect Prompt Injection Surface: The skill is designed to ingest and process text data from untrusted code files, creating a potential exposure surface if the analyzed codebase contains adversarial content.
  • Ingestion points: Scans .cs, .csproj, and .sln files within the current workspace as outlined in Step 1 of SKILL.md.
  • Boundary markers: Specific delimiters or prompt boundary instructions to handle untrusted code comments or embedded strings are absent.
  • Capability inventory: Utilizes workspace file-listing, text-searching, and file-reading tools.
  • Sanitization: Canonical path verification is enforced to maintain strict workspace boundaries, though text-level filtering of input code is absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:16 AM
Security Audit — agent-trust-hub — detect-static-dependencies