skills/larksuite/cli/lark-event/Gen Agent Trust Hub

lark-event

Pass

Audited by Gen Agent Trust Hub on May 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data (Lark/Feishu event payloads, such as chat messages) into the agent's context, creating a surface for indirect prompt injection.\n
  • Ingestion points: Event data consumed via lark-cli event consume in NDJSON format, specifically im.message.receive_v1.\n
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are documented to isolate the ingested event content from the agent's operational instructions.\n
  • Capability inventory: The agent using this skill typically has access to lark-cli which allows for sending messages, reading contacts, and other interactive capabilities as referenced in the skill's dependencies.\n
  • Sanitization: No explicit sanitization or filtering of the event content is suggested beyond structural transformation using jq.
Audit Metadata
Risk Level
SAFE
Analyzed
May 27, 2026, 03:07 AM
Security Audit — agent-trust-hub — lark-event