Set up a scheduled agent that reads a small team's existing production logs, flags suspicious activity, and pages a human, without a SIEM or security staff. Use when the user mentions 'log watch,' 'watch my logs,' 'alert me if someone is attacking,' 'no SIEM,' 'poor man's SIEM,' 'agent reads CloudTrail,' 'cron job that checks logs,' 'page me on suspicious logins,' 'Vercel logs alerting,' 'Sentry security alerts,' 'Supabase auth logs,' 'Stripe dispute spike,' 'credential stuffing alert,' 'two-stage classifier,' 'Haiku then Sonnet,' 'log monitoring cost,' or has Vercel / Heroku / Render / Sentry / Postgres / Stripe / Cloudflare / CloudTrail / GitHub logs and wants to know when something bad happens.
96%
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 required workflow ingests external production logs, request paths, user agents, and error messages from services like Vercel, Heroku, GitHub, and SQL databases, which can contain outsider-authored free text (indirect prompt injection).
briiirussell/cybersecurity-skills
18642b2
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.