merge-pr-check

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted external content from Gitee pull requests, such as reviewer comments and code changes, which could include instructions intended to improperly influence the merge recommendation report.
  • Ingestion points: External data is ingested from the Gitee MCP tools get_pull_detail, list_comments, and get_diff_files as seen in SKILL.md.
  • Boundary markers: Missing; the skill does not provide clear delimiters or instructions to the model to ignore instructions hidden within the PR data.
  • Capability inventory: The tool includes the ability to perform repository merges via the merge_pull tool (SKILL.md), allowing persistent changes to source code.
  • Sanitization: No validation or sanitization is performed on the PR data or comments before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:35 AM