Triage a batch of raw security findings. Verify each is real, collapse duplicates, re-rank by derived exploitability, and tag with an owner. Takes a directory or file of scanner output and writes TRIAGE.json + TRIAGE.md sorted by what actually needs engineering attention. Use when asked to "triage findings", "validate scanner output", "prioritize vulns", or "review the backlog". Runs interactively by default; pass --auto to skip the interview.
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 triage workflow ingests security scanner output from local files or directories, which can contain attacker-authored descriptions or findings designed to trigger prompt injection when processed and evaluated by the agent.
Q00/ouroboros
592c667
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.