Conduct external recon using OSINT techniques to map an organization's external attack surface without touching target systems, gathering DNS records, certificate transparency logs, search results, social media, code repositories, and breach databases into a target profile. Use for the passive info-gathering phase of a pentest, external footprinting, or collecting employee/email intel for a social engineering campaign.
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The skill searches external code repositories on GitHub and queries third-party OSINT services whose results can contain outsider-authored text, but the agent actively searches/fetches specific targets rather than passively consuming unselected feeds.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.