vcr-http-recording

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill records and replays HTTP interactions from arbitrary external APIs (e.g., examples using requests.get in SKILL.md and scripts/vcr-cassette.py and the "llm-api-testing" section that records LLM API responses), so the agent ingests untrusted third-party responses as part of its workflow which could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:45 PM