feishu-doc
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill implements standard document management functionality for Feishu and does not contain any malicious code, obfuscation, or unauthorized data access behaviors.\n- [NO_CODE]: The skill consists entirely of configuration and documentation files with no executable scripts or external code dependencies included.\n- [PROMPT_INJECTION]: The skill interacts with external document data, which creates a surface for indirect prompt injection.\n
- Ingestion points: External data enters the agent context via the
readandlist_blocksactions defined inSKILL.mdwhen retrieving Feishu document content.\n - Boundary markers: The skill documentation does not specify the use of delimiters or instructions to ignore embedded commands within the document text.\n
- Capability inventory: Across all actions in
SKILL.md, the skill can read, write, append, update, and delete document blocks, representing significant modification capabilities if the agent is influenced by document content.\n - Sanitization: No content sanitization or validation logic is defined for the document data retrieved from the Feishu API.
Audit Metadata