recon-fire-restoration

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs the agent to retrieve and display potentially sensitive files (e.g., wp-content/debug.log, /.env, wp-config.php.bak) using curl and head, which will expose any embedded credentials or secrets verbatim in the agent's output.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is a targeted reconnaissance-and-exploitation guide that instructs how to locate and extract customer PII, abuse CORS for credential reflection, and enumerate sensitive files—behavior consistent with intentional data exfiltration and credential theft.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow uses runtime curl to fetch outsider-authored web content from arbitrary target domains (e.g., crt.sh public index and https://$TARGET/... debug logs/config files), and those responses are read as prose by the LLM via the agent’s tool outputs (e.g., head -100 of debug.log).