recon-daycare

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes commands that fetch and print debug logs, grep for DB_PASSWORD/DB_USER and API key patterns (pk_/sq0idp), and download/exfiltrate files — all of which would expose secret values verbatim if executed or reported, so the LLM would be required to handle/output secrets directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is explicitly malicious: it documents targeted reconnaissance and concrete exfiltration/attack steps to harvest PII (including minors' data), credentials, and achieve RCE on daycare/childcare sites.

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 arbitrary outsider-authored web content from target domains (e.g., directory listings, debug logs, plugin readme.txt, and form/upload pages), which would be ingested as readable text by the agent/LLM if the tool output is passed into the LLM context.