feishu-cli-sheet
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill repeatedly instructs using tokens (e.g., , <image_token>) as direct CLI arguments, which encourages embedding secret/API tokens verbatim in commands and outputs, creating an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill reads arbitrary user-provided Feishu spreadsheet content via commands like "feishu-cli sheet read", "read-rich", and "read-plain" (ingesting data from Feishu sheets through the V2/V3 APIs), so it clearly consumes untrusted, user-generated third-party content that could carry indirect prompt injection.
Audit Metadata