feishu-doc-reader

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to make local scripts executable and run them to interact with the Feishu API. This is expected behavior for this type of integration.
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by reading content from external documents. 1. Ingestion points: Fetches document blocks, tables, and text from the Feishu Open API. 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation. 3. Capability inventory: The skill can execute local shell scripts and Python scripts. 4. Sanitization: There is no evidence of sanitization or filtering applied to the fetched document data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 04:28 PM
Security Audit — agent-trust-hub — feishu-doc-reader