SKILLEMALL.ai
GitHub ↗ RU Sign in

CC detecting-oauth-token-theft

Detect and respond to OAuth token theft and replay in Microsoft Entra ID (Azure AD), covering access token theft, refresh token replay, Primary Refresh Token (PRT) abuse, pass-the-cookie attacks, and Token Protection conditional access policies. Use for impossible-travel or anomalous token-usage alerts, suspected session hijacking, sign-in log analysis, or configuring token-binding defenses in Azure/M365.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 2 825 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Detect and respond to OAuth token theft and replay in Microsoft Entra ID (Azure AD), covering access token theft, refresh token replay, Primary Refresh Token…

As a process C 64/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice

IntegrationAzureSecuritytype 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
89/100
safety, quality, tests
Safety 60%
96
Quality 40%
79
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Exfiltration net-credential-use references/api-reference.md:6
      Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
      curl -H "Authorization: Bearer $MS_TOKEN" \
      security skill
    • low Exfiltration net-credential-use references/api-reference.md:25
      Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
      curl -H "Authorization: SSWS $OKTA_TOKEN" \
      security skill
    • low Secrets in code secret-high-entropy-token SKILL.md:226
      High-entropy token-like string (may be an id, hash or a credential)
      Get-…ant -UserId "us…@….com" |
    • low Secrets in code secret-high-entropy-token SKILL.md:230
      High-entropy token-like string (may be an id, hash or a credential)
      Remo…ant -OAu…tId "<grant-id>"

    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"
    • note frontmatter-key unknown frontmatter key "mitre_f3"

    Process rating: all ten parameters 64/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 2 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 25 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2825 tokens
    • 100Progress reporting. Reports progress

    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
    • +3Output format is not stated: the model decides each time
    • -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 408: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 25 items
    • +4Has examples (8 code blocks)
    • +1License stated

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