skills/magic5644/skills/pr-review/Gen Agent Trust Hub

pr-review

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @magic5644/graph-it-live package globally from the npm registry to enable its core analysis features.
  • [EXTERNAL_DOWNLOADS]: References a reusable GitHub Action located at magic5644/Graph-It-Live for setting up automated PR review gates.
  • [COMMAND_EXECUTION]: Executes shell commands including git fetch and various graph-it subcommands to perform repository indexing and diff analysis.
  • [PROMPT_INJECTION]: The skill identifies as having an attack surface for indirect prompt injection because it processes untrusted data from Git diffs and pull requests.
  • Ingestion points: Pull request branch diffs and source code files (SKILL.md).
  • Boundary markers: None explicitly specified for separating code content from analysis instructions.
  • Capability inventory: Executes subprocesses through the graph-it CLI tool across all scripts.
  • Sanitization: No explicit sanitization or escaping of the processed code content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 06:32 AM
Security Audit — agent-trust-hub — pr-review