close-issue-flow
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (Gitee issue and pull request content) which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill fetches issue titles, descriptions, and comments via the
get_repo_issue_detailtool (SKILL.md, Step 1) and pull request descriptions vialist_repo_pulls(SKILL.md, Step 2). - Boundary markers: The instructions do not define any explicit boundary markers or warnings to the agent to disregard instructions embedded within the fetched data.
- Capability inventory: The skill has the capability to post comments to issues (
create_comment) and modify the state of an issue (update_issue) based on the retrieved information. - Sanitization: No sanitization, filtering, or validation of the external content is performed before the agent uses it to generate summaries or take actions.
Audit Metadata