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

implement-issue

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified through the ingestion and processing of untrusted Gitee issue data.
  • Ingestion points: External data is ingested via the get_repo_issue_detail and list_issue_comments tools in SKILL.md.
  • Boundary markers: None; the instructions do not include markers or warnings to separate user-provided issue content from the agent's instructions.
  • Capability inventory: The skill enables code implementation and pull request creation via the create_pull tool, allowing potentially malicious input to influence code changes.
  • Sanitization: No validation or sanitization of the issue content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 05:08 AM