feishu-card

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill obtains authentication tokens by executing a local script feishu-auth.js from the associated feishu-user-auth skill directory. This is used to authorize API calls to Feishu.
  • [PROMPT_INJECTION]: The skill populates message card templates in the references/ directory using placeholders (e.g., {{description}}, {{details}}) filled with user-provided content. This represents a potential surface for indirect prompt injection if malicious instructions are embedded in the source data.
  • Ingestion points: User-provided strings for template variables in references/ JSON files.
  • Boundary markers: None identified in the skill's instructions or template files.
  • Capability inventory: Token retrieval via command execution; outbound network requests to the Feishu API (POST/PATCH).
  • Sanitization: No explicit sanitization or validation of the input data before interpolation into the card templates is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 07:42 PM