Ask me what skills you need
What are you building?
Tell me what you're working on and I'll find the best agent skills for you.
Hunt Server-Side Request Forgery (CWE-918) through taint analysis from user-controlled URLs to HTTP client sinks. Covers cloud metadata pivoting, DNS rebinding, gopher smuggling, and the IMDSv1 → IAM role chain that turns SSRF into RCE.
SSRF is one of the highest-yield vuln classes for 0-day work because (a) it's often medium severity in isolation but chains to critical when it reaches cloud metadata, internal admin panels, or unprotected Redis/Elasticsearch, and (b) modern frameworks have dozens of bypass classes that scanners miss.
Look for any parameter that gets fed into an HTTP client:
requests.get(user_url), httpx.get, urllib.request.urlopen, aiohttp.getfetch(userUrl), axios.get, http.request, got, node-fetchHttpURLConnection, HttpClient.send, URL.openConnection, OkHttpClienthttp.Get(u), http.NewRequest, net.Dial("tcp", u)Net::HTTP.get, URI.open, Faraday.getfile_get_contents($url), curl_exec, fsockopenGrep patterns to run via bash:
semgrep --config p/ssrf /workspace/src --sarif -o /workspace/sem-ssrf.sarif
grep -rE 'requests\.get\(|httpx\.|urllib.*urlopen|fetch\(|axios\.|http\.Get\(|URL\(' /workspace/src
npx skills add PurpleAILAB/Decepticon --skill ssrfHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
Very clear and well structured, with almost no room for misunderstanding.
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
Highly actionable with clear, concrete steps that an agent can follow directly.