review-pr

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from Gitee Pull Requests, such as titles, descriptions, and file contents, which could contain malicious instructions designed to manipulate the AI's review behavior.
  • Ingestion points: Untrusted data is retrieved using tools like get_pull_detail, list_pull_comments, and get_file_content as outlined in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or specific directives to the AI to ignore instructions embedded within the PR data being analyzed.
  • Capability inventory: The skill has the ability to post comments back to the repository using the comment_pull tool, which could be used to spread malicious content if the AI is successfully injected.
  • Sanitization: The skill does not implement any sanitization or validation of the ingested content before it is passed to the AI for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 01:58 PM