feishu-cli-search

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute feishu-cli commands for authentication and searching. This allows the agent to interact with the local system and the Feishu API.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from Feishu documents and messages. \n
  • Ingestion points: Results from feishu-cli search docs and feishu-cli search messages are brought into the agent's context. \n
  • Boundary markers: There are no explicit markers or instructions provided to the agent to treat the search results as untrusted data or to ignore embedded instructions. \n
  • Capability inventory: The skill utilizes the Bash tool, which provides a broad execution environment. \n
  • Sanitization: There is no evidence of sanitization or filtering of the retrieved content before it is processed.
  • [CREDENTIALS_UNSAFE]: The skill manages sensitive Feishu User Access Tokens. These tokens are stored in the local file ~/.feishu-cli/token.json. Additionally, the authentication flow requires users to manually provide a callback URL which contains sensitive authorization codes and state parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 01:46 AM