pr-submission-review

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is designed to ingest and process untrusted data from pull request metadata and code diffs.
  • Ingestion points: Untrusted data enters the agent context through the fetch_pr_context and audit_pr_changes tools, which retrieve pull request content (referenced in scripts/fetch_pr_context.py and scripts/audit_pr_changes.py).
  • Boundary markers: The tool definitions and skill instructions do not include boundary markers or specific instructions for the agent to ignore potentially malicious content embedded in the PR data.
  • Capability inventory: The skill has the capability to write to the workspace filesystem via the write_pr_review tool (scripts/write_pr_review.py).
  • Sanitization: It is not possible to verify if input sanitization or validation is implemented because the tool scripts are not provided in the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 09:12 PM
Security Audit — agent-trust-hub — pr-submission-review