SKILLEMALL.ai
GitHub ↗ RU Sign in

BC hunt-subdomain

Hunting skill for subdomain takeover vulnerabilities. Includes modern provider fingerprints — Microsoft Azure DevOps `cloudapp.azure.com` regional-pool re-issue (1-click OAuth ATO via wildcard `reply_to`, Binary Security), Zendesk help-desk takeover → email interception → password reset chain (0xprial writeup), Vercel `cname.vercel-dns.com` deleted-project takeover, plus general Fastly CDN service re-attach and S3 dangling-bucket cookie-scope techniques. Use when hunting subdomain takeover — emphasis on ATO-chain primitives (OAuth `redirect_uri`, cookie-domain, email DNS).

elementalsouls/Claude-BugHunter Agent Skills author: elementalsouls 1 file body ≈ 6 015 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Hunting skill for subdomain takeover vulnerabilities.

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAzureGitHubGitLabAWSInfrastructureSecurityResearchtype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
88/100
safety, quality, tests
Safety 60%
99
Quality 40%
72
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • low Risky intent intent-offensive-security SKILL.md:304
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Impact:** Highly-effective phishing campaign exploiting the parent brand. Victims trust the email because every authentication check passes. Credential harvesting, BEC fraud, supply-chain access.

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6015 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "sources"
  • note frontmatter-key unknown frontmatter key "report_count"
  • note edit-residue the text marks something as outdated (lines 263, 265, 272, 279): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 50/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 70Execution cost. Instruction body is 6015 tokens
  • 100Steps. 123 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 579: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 123 items
  • +4Has examples (10 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.