lark-vc-agent
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a compatibility layer for the lark-meeting skill. It does not contain any executable code or sensitive operations itself.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read another file (
../lark-meeting/SKILL.md) for instructions. 1. Ingestion points: The agent is instructed to read instructions from../lark-meeting/SKILL.md(relative path). 2. Boundary markers: None present in this file. 3. Capability inventory: No command execution, network access, or file-writing capabilities are defined in this file. 4. Sanitization: None present. This structure is a standard vendor-provided redirection logic for modular skill compatibility and represents a low-risk surface.
Audit Metadata