ppocrv5
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: 1.00). The prompt explicitly asks the agent to request and parse user-provided API_URL/TOKEN and then embed the parsed token verbatim into a shell command (python ... --token "PARSED_TOKEN"), forcing the LLM to handle and output secrets directly.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill accepts arbitrary public URLs for images/PDFs (e.g., "Extract text from URLs" and the required commands using --file-url) and mandates the agent to read and display the complete OCR'd text (result.full_text), so it clearly ingests untrusted third-party content that could carry indirect prompt injection.
Audit Metadata