ai-podcast-creation
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.90). High risk: the skill instructs piping a remote shell script from an unfamiliar domain (https://cli.inference.sh) directly to sh—downloading and executing scripts from an unverified site is a common malware distribution vector even if the domain itself isn't an obvious typosquat.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the LLM to "Read this document" with a placeholder "" (NotebookLM-Style Content) and shows media-merger examples that accept audio file URLs ("", ""), which means it can ingest arbitrary user-provided or public web content that could carry indirect prompt injections.
Audit Metadata