SKILLEMALL.ai
GitHub ↗ RU Sign in

CC performing-ssrf-vulnerability-exploitation

Tests web application URL parameters for Server-Side Request Forgery by probing cloud metadata endpoints (AWS/GCP/Azure at 169.254.169.254), internal network services, and protocol handlers (file://, gopher://, dict://) using a Python script, including IP-encoding bypass and DNS rebinding checks. Use during authorized penetration testing to confirm SSRF in a URL-fetching parameter and generate a vulnerability report.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 385 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Tests web application URL parameters for Server-Side Request Forgery by probing cloud metadata endpoints (AWS/GCP/Azure at 169.254.169.254), internal network…

As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, progress reporting

ProcedureAWSGoogle CloudAzureSecurityData 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
C
86/100
safety, quality, tests
Safety 60%
91
Quality 40%
79
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
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

    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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Exfiltration exfil-webhook-url scripts/agent.py:33
      Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
      {"name": "Redirect bypass", "url": "http://spoofed.burpcollaborator.net/redirect?url=…"},
      quoted
    • low Secrets in code secret-high-entropy-token references/api-reference.md:7
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | AWS IMDSv2 | `http://169.254.169.254/latest/api/token` | `X-aw…ds: 21600` |
      table
    • low Risky intent intent-offensive-security references/api-reference.md:34
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Internal service access | Lateral movement | High |
    • low Risky intent intent-offensive-security SKILL.md:8
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      rebinding checks. Use during authorized penetration testing to confirm SSRF
    • low Risky intent intent-offensive-security SKILL.md:62
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # For authorized penetration testing and lab environments only

    Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "domain"
    • note frontmatter-key unknown frontmatter key "subdomain"
    • note frontmatter-key unknown frontmatter key "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"

    Process rating: all ten parameters 59/100

    • 0Result and completion. Does not say what the result is
    • 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 (python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 17 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 385 tokens
    • 100Running it twice. No mutating operations

    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
    • -2localhost URLs: will not work for another user
    • -41 reference files, but SKILL.md never points to them: the model will not open them
    • +2Single-language instructions
    • +3Description length 420: enough signal without eating the budget
    • +4Structure: 5 headings
    • +3Step-by-step instructions: 17 items
    • +4Has examples (2 code blocks)
    • +3All 1 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.