Skills
skills/oschina/gitee-agent-skills/close-issue-flow/Gen Agent Trust Hub

close-issue-flow

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted data from Gitee repository objects.
  • Ingestion points: The agent retrieves issue titles, descriptions, and comments using get_repo_issue_detail, and pull request descriptions via list_repo_pulls (file: SKILL.md).
  • Boundary markers: The instructions do not define boundary markers or explicit 'ignore instructions' directives for the content retrieved from Gitee.
  • Capability inventory: The skill has access to tools that can modify repository state, including comment_issue and update_issue (file: SKILL.md).
  • Sanitization: There is no evidence of sanitization or validation of the retrieved text before it is used to determine the workflow or included in summaries.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 05:08 AM