create-pr

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data when analyzing branch differences to generate Pull Request descriptions.
  • Ingestion points: Branch diff data returned by the compare_branches_tags tool (Step 2).
  • Boundary markers: Not explicitly defined for the diff content analysis.
  • Capability inventory: The skill can perform network write operations via the create_pull tool (Step 5).
  • Sanitization: No specific sanitization or filtering of the diff content is mentioned before it is processed by the LLM to generate the PR title and body.
  • [EXTERNAL_DOWNLOADS]: The documentation suggests the use of the mcporter CLI tool. As this is a resource associated with the Gitee ecosystem provided by the vendor, it is noted as an expected integration for this skill's use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 02:21 PM