SKILLEMALL.ai
GitHub ↗ RU Sign in

BB hunt-csrf

Hunting skill for csrf vulnerabilities. Built from 15 public bug bounty reports including modern variants — SameSite=Lax sibling-subdomain bypass (Argo CD CVE-2024-22424), GraphQL mutations-via-GET (GitLab $3,370), framework-wide CSRF middleware disabled (Stripe Dashboard $5,000), path-traversal CSRF-token bypass (GitHub Enterprise CVE-2022-23732 $10k), Origin-omission bypass (TikTok $2,500), OAuth-state null-byte (Streamlabs), WebSocket CSRF / CSWSH (Coda), default-SameSite email-change → ATO (YoYo Games $400), social-account-link CSRF (HackerOne), JSON-CSRF via text/plain on email-change (TikTok $500). Use when hunting modern CSRF — heavy emphasis on chain-to-ATO patterns.

elementalsouls/Claude-BugHunter Agent Skills author: elementalsouls 1 file body ≈ 6 434 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Hunting skill for csrf vulnerabilities.

As a process B 70/100 · Nearly there — weak spots: when it triggers

IntegrationStripeGitHubGitLabSecurityData and analyticstype 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
86/100
safety, quality, tests
Safety 60%
94
Quality 40%
75
Run on models
none yet
Process rating
B
70/100
Nearly there
When it triggers w 12
20
Tools and files w 18
60
Result and completion w 14
60
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Risky intent intent-offensive-security SKILL.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    description: Hunting skill for csrf vulnerabilities. Built from 15 public bug bounty reports including modern variants — SameSite=Lax sibling-subdomain bypass (Argo CD CVE-…424), GraphQL mutatio

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6434 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 346): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 70/100

  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (web, node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6434 tokens
  • 85Steps. 71 steps, 1 vague phrases
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 13 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 683: enough signal without eating the budget
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 71 items
  • +3Output format is stated explicitly
  • +4Has examples (10 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.