SKILLEMALL.ai
GitHub ↗ RU Sign in

CB performing-oauth-scope-minimization-review

Performs OAuth 2.0 scope minimization review to identify over-permissioned third-party application integrations, excessive API scopes, unused token grants, and risky OAuth consent patterns across identity providers and SaaS platforms. Activates for requests involving OAuth scope audit, API permission review, third-party app risk assessment, or consent grant minimization.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 5 854 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Performs OAuth 2.0 scope minimization review to identify over-permissioned third-party application integrations, excessive API scopes, unused token grants…

As a process B 69/100 · Nearly there — weak spots: failures and branches, running it twice, progress reporting

IntegrationSecuritytype 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
88/100
safety, quality, tests
Safety 60%
99
Quality 40%
72
Run on models
none yet
Process rating
B
69/100
Nearly there
Failures and branches w 10
0
Progress reporting w 2
0
Running it twice w 4
30
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 Secrets in code secret-password-literal scripts/agent.py:196
    Hard-coded password / key literal (may be an example)
    client_secret = sys.argv[3]

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5854 tokens (recommended < 5000); move details to references/
  • 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"
  • note frontmatter-key unknown frontmatter key "mitre_f3"
  • note edit-residue the text marks something as outdated (lines 518): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 69/100

  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 2 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 5854 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 29 steps
  • 100Consistency. Name and required fields are in place

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
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 373: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 29 items
  • +3Output format is stated explicitly
  • +4Has examples (6 code blocks)
  • +1License stated

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