feishu-cli-vc

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the 'feishu-cli' tool from the author's GitHub repository (github.com/riba2534/feishu-cli) as a prerequisite for functionality. This is a vendor-owned resource managed by the skill's author.\n- [COMMAND_EXECUTION]: The skill uses the 'feishu-cli' binary through a shell to search for conferences, retrieve meeting notes, and fetch transcript metadata. These commands are executed locally using the agent's Bash tool.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the processing of external meeting data.\n
  • Ingestion points: Meeting transcripts, structured summaries, and metadata are ingested into the agent context via the vc notes and minutes get commands (SKILL.md).\n
  • Boundary markers: Absent. The skill instructions do not provide delimiters or negative constraints to prevent the agent from following instructions embedded within the Feishu meeting content.\n
  • Capability inventory: The agent possesses the Bash and Read capabilities, which could be leveraged if malicious instructions in a meeting transcript are followed (SKILL.md).\n
  • Sanitization: Absent. There is no evidence of content filtering or validation for the data retrieved from the Feishu platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 07:07 PM