recon-pet-grooming

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill document contains targeted reconnaissance and exploitation instructions (curling debug logs, enumerating booking APIs for IDOR, harvesting photo EXIF, locating uploads and API keys) that enable deliberate data exfiltration and credential/secret discovery of pet owner PII and access codes.

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses runtime curl to fetch arbitrary outsider-controlled web pages/files (e.g., /wp-content/debug.log, /wp-content/uploads/..., /gallery) and then pipes the fetched body text through grep/jq/head, which becomes LLM-readable content via the agent’s tool output—enabling indirect prompt injection from outsider-authored free text.