Skills
skills/zephyrwang6/allskills/feishu-wiki/Gen Agent Trust Hub

feishu-wiki

Pass

Audited by Gen Agent Trust Hub on May 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from external Feishu sources.
  • Ingestion points: scripts/read_bitable.py fetches table records via get_table_records, and scripts/list_wiki.py retrieves node titles through get_node_info.
  • Boundary markers: The instructions do not define delimiters or provide guidance to the agent to ignore instructions embedded within the retrieved content.
  • Capability inventory: The skill can write to the Feishu Wiki (scripts/save_to_wiki.py), append records to Bitables (scripts/add_records.py), and read local file content.
  • Sanitization: No sanitization or validation is performed on the content fetched from the Feishu API before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 24, 2026, 12:06 PM
Security Audit — agent-trust-hub — feishu-wiki