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
Risk Level
SAFE
Analyzed
Sep 29, 2026, 12:36 AM