hunt-agent-prompt-extraction
Warn
Audited by Snyk on Nov 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill contains a runnable Python script that sends HTTP POST requests to a target agent chat endpoint (
https://target/agent/chat) in order to test and extract system prompts and guardrails.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata