gitnexus-pr-review

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands including gh pr diff to fetch pull request data and node .gitnexus/run.cjs analyze to update the local analysis index. These are standard operations for a development-oriented tool.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it ingests and processes untrusted pull request diffs. An attacker could include malicious instructions in code comments or commit messages within a PR to manipulate the agent's review. 1. Ingestion points: PR diff content via gh pr diff (SKILL.md). 2. Boundary markers: No explicit markers or 'ignore' instructions are used to separate PR content from the agent's logic. 3. Capability inventory: The agent has access to terminal execution and GitNexus-specific tools (detect_changes, impact, context). 4. Sanitization: No sanitization or validation of the ingested diff content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 12:54 AM
Security Audit — agent-trust-hub — gitnexus-pr-review