feishu-update-doc

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements expected functionality for managing Feishu documents, providing clear instructions for locating and updating content via selection patterns.- [PROMPT_INJECTION]: The skill serves as a surface for indirect prompt injection because it processes markdown content that could originate from untrusted sources.
  • Ingestion points: Content provided in the markdown parameter and document text matched via patterns documented in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided.
  • Capability inventory: The skill can append, replace, and delete content, including overwriting entire documents.
  • Sanitization: No input validation or sanitization of the markdown content is identified in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 04:30 AM