close-issue-flow
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external, untrusted sources within Gitee.\n
- Ingestion points: The skill retrieves untrusted content from Issue titles, descriptions, and comments via
get_repo_issue_detailand from PR descriptions vialist_repo_pullsas defined in SKILL.md.\n - Boundary markers: There are no explicit instructions or delimiters used to separate user-provided content from the agent's instructions, nor are there warnings to ignore instructions embedded in the external data.\n
- Capability inventory: The agent has the capability to interact with the Gitee API to post comments (
comment_issue) and modify issue states (update_issue) based on the processed data, as outlined in SKILL.md.\n - Sanitization: No sanitization or validation of the retrieved text is specified before it is processed by the agent.
Audit Metadata