pull-request-diff-analyzer

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from pull request metadata.
  • Ingestion points: The gh pr view command in SKILL.md (Step 2) retrieves external data from the title, body, comments, reviews, and issues fields.
  • Boundary markers: Absent. The instructions do not define delimiters or provide specific directives for the agent to ignore potential instructions embedded within the PR content.
  • Capability inventory: The skill uses git and gh (GitHub CLI) for repository and PR analysis. No dangerous file-write, network exfiltration, or arbitrary code execution capabilities were identified.
  • Sanitization: Absent. There is no evidence of sanitization or validation for the data ingested from the PR context.
  • [COMMAND_EXECUTION]: The skill uses standard CLI tools to gather repository data.
  • Evidence: It executes shell commands including git branch, git diff, and gh pr view to extract branch names, code changes, and pull request details.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 06:37 PM
Security Audit — agent-trust-hub — pull-request-diff-analyzer