stale-pr-reminder

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill performs read-only operations on Gitee repositories to identify inactive pull requests based on timestamps.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of pull request titles and comments from Gitee repositories.
  • Ingestion points: Pull request metadata (titles) and comments are retrieved via get_pull_detail and list_pull_comments (SKILL.md).
  • Boundary markers: Absent. The skill does not explicitly instruct the agent to ignore instructions embedded in the PR content.
  • Capability inventory: The skill only uses Gitee read tools (list_repo_pulls, get_pull_detail, list_pull_comments) and does not possess capabilities for file writing, code execution, or non-Gitee network operations.
  • Sanitization: Absent. PR data is processed as-is.
  • Note: While the ingestion surface exists, the lack of dangerous tools makes the risk of this indirect injection negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 05:08 AM