recon-salons

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an offensive reconnaissance playbook that explicitly instructs how to enumerate booking APIs, extract customer PII and API keys, and exploit IDOR/cancellation endpoints — enabling unauthorized data exfiltration and abuse.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md’s required workflow uses runtime curl to fetch booking pages and API responses from the target’s public web endpoints (outsider-authored free text/JSON from arbitrary third-party sites), which would be ingested into the agent’s LLM context if the tool output is passed through.