create-feishu-doc

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it interpolates user-supplied data (document title and content) directly into browser automation commands such as agent-browser type and agent-browser fill. Malicious instructions embedded in the user content could theoretically attempt to influence the agent's execution flow.
  • Ingestion points: Document title and content placeholders in SKILL.md (Step 7 and Step 8).
  • Boundary markers: Absent; user input is not wrapped in delimiters or accompanied by instructions to ignore embedded commands.
  • Capability inventory: The skill utilizes agent-browser for navigation, UI interaction, and capturing snapshots/screenshots across ALL steps.
  • Sanitization: No sanitization or validation of the user-provided strings is performed before they are processed by the browser automation tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 02:56 AM