doubleword-batch
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 prompt's examples show and encourage embedding API keys directly in code and request headers (e.g., api_key="YOUR_API_KEY", Authorization: "Bearer YOUR_API_KEY"), which requires the agent to place secret values verbatim rather than keeping them in secure env vars or external credential stores.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to download and read batch job outputs from the public Doubleword API (e.g., GET https://api.doubleword.ai/v1/files/{batch.output_file_id}/content under "Download Results"), which can contain arbitrary user- or model-generated content from third parties that the agent is expected to read and interpret.
Audit Metadata