skills/mgiovani/skills/review-deps/Gen Agent Trust Hub

review-deps

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes native security audit commands across multiple ecosystems, including npm audit, pip-audit, cargo audit, go list, composer audit, and dotnet list package. These commands are used as intended for security analysis tasks.\n- [EXTERNAL_DOWNLOADS]: Utilizes the GitHub CLI to fetch repository-specific Dependabot alerts from GitHub's official API. This provides a cloud-based view of security risks alongside local analysis using a trusted platform source.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by reading and processing project manifest files (such as package.json or Cargo.toml). This untrusted external data is subsequently passed to analysis agents.\n
  • Ingestion points: SKILL.md (Phase 1 and 2) reads various project manifest files and security tool outputs.\n
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the content of ingested manifests.\n
  • Capability inventory: The skill uses a broad set of shell commands for auditing different software stacks.\n
  • Sanitization: There is no explicit sanitization performed on the data retrieved from manifests or tool outputs before it is analyzed by agents.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 04:32 PM
Security Audit — agent-trust-hub — review-deps