feishu-calendar
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface common to data-processing tools.
- Ingestion points: Event summaries and descriptions returned by search and list actions (SKILL.md).
- Boundary markers: Absent; no instructions for using delimiters or ignoring embedded instructions are provided.
- Capability inventory: Network-based tool calls for creating and modifying calendar events (SKILL.md).
- Sanitization: Absent; no filtering or validation of external event content is specified.
- Note: This surface is considered safe as it is essential to the primary functionality of the skill.
- [SAFE]: No hardcoded credentials, sensitive file access, or unauthorized network exfiltration patterns were detected.
- [SAFE]: Resource identifiers (ou_, oc_, omm_) and operational logic are consistent with the legitimate Feishu/Lark platform managed by the vendor larksuite.
Audit Metadata