feishu-docs

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from external cloud documents and possesses high-privilege capabilities.
  • Ingestion points: Document content is ingested through commands like feishu-docs read, feishu-docs cat, and feishu-docs search (SKILL.md).
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are specified when reading document content.
  • Capability inventory: The skill can create, update, delete, and change sharing permissions (including public exposure) of documents via feishu-docs create, feishu-docs update, feishu-docs delete, and feishu-docs share (SKILL.md).
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from documents before it is presented to the agent.
  • [COMMAND_EXECUTION]: The skill's core functionality relies on executing the feishu-docs CLI. While this is the intended use case, the broad scope of the tool—including the ability to delete resources and modify permissions—poses a risk if the agent is manipulated via malicious document content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 03:34 PM