recon-tree-services

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs curling pages and grepping/extracting Google Maps API keys (AIza...) and fetching wp-content/debug.log, which requires capturing and outputting secret/API key values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document is high-risk: it explicitly instructs how to locate and harvest customer PII, exposed API keys, and unauthenticated CRM portals and lists bypass techniques to access and exfiltrate that data.

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

• Third-party content exposure detected (high risk: 0.75). This skill’s required workflow uses runtime curl to fetch arbitrary target web pages (outsider-authored free text from public sites/customer portals) and then runs grep/head over the downloaded HTML/log content, which can include attacker-controlled text that would be ingested by the agent if its outputs are passed into the LLM context.