feishu-cli-platform

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Feishu API, such as message contents and cloud documents. While this introduces a surface for indirect prompt injection, the skill's primary focus is on searching and displaying information rather than autonomous execution of data-derived instructions. Mandatory Evidence Chain: 1. Ingestion points: Search results for messages and docs (references/workflows/search/workflow.md). 2. Boundary markers: Not explicitly defined in instructions. 3. Capability inventory: Bash execution, curl, and file writing (SKILL.md). 4. Sanitization: Relies on jq and CLI tool output formatting.
  • [COMMAND_EXECUTION]: The skill enables execution of the feishu-cli tool along with standard utilities like curl, jq, and python3. These tools are appropriately scoped to the skill's purpose of managing Feishu platform resources and do not exhibit malicious patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:39 PM
Security Audit — agent-trust-hub — feishu-cli-platform