recon-landscaping

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly downloads debug.log and greps for DB_PASSWORD/DB_USER/DB_NAME/API_KEY (and extracts webhook URLs), which instructs the agent to read and output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is a targeted offensive reconnaissance playbook: it instructs scanning owners' sites, harvesting debug logs and credentials, extracting EXIF geolocation from photos, enumerating plugins/versions for exploitation, and finding/modifying webhooks (SSRF/CSRF) — all clearly enabling unauthorized data exfiltration and exploitation.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required workflow uses runtime curl to fetch outsider-authored web content from arbitrary target domains (e.g., crt.sh JSON, HTML bodies, debug.log, plugin readme.txt, and source pages) and then parses/prints readable text into the agent’s context.