feishu-openapi-skill

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches a curated OpenAPI schema from the author's official GitHub repository.
  • [CREDENTIALS_UNSAFE]: Demonstrates secure credential handling by instructing the use of environment variables (env:FEISHU_APP_ID, env:FEISHU_APP_SECRET) for Feishu/Lark authentication rather than hardcoded secrets.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through its message-reading capabilities.
  • Ingestion points: IM message content retrieved via get:/im/v1/messages and get:/im/v1/messages/{message_id} as defined in references/feishu-im.openapi.json.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used for processing retrieved message text.
  • Capability inventory: Capabilities include sending messages (post:/im/v1/messages) and uploading files (post:/im/v1/files).
  • Sanitization: No sanitization or validation of the ingested message content is explicitly performed by the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 03:14 AM