SKILLEMALL.ai
GitHub ↗ RU Sign in

BC hunting-saas-sso-token-abuse

Hunts for stolen-session and OAuth/PRT token replay (T1550.001) by correlating Microsoft Entra ID SigninLogs SessionId/UniqueTokenIdentifier fields and Okta System Log sso/session events to spot impossible travel, refresh-token reuse, and token use from anomalous ASNs. Use when hunting MFA-bypass via stolen cookies/tokens, investigating impossible-travel alerts, or scoping SaaS lateral movement after phishing.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 5 files · 1 script body ≈ 2 707 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Hunts for stolen-session and OAuth/PRT token replay (T1550.001) by correlating Microsoft Entra ID SigninLogs SessionId/UniqueTokenIdentifier fields and Okta…

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

IntegrationAzurePeople and hiringtype 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
90/100
safety, quality, tests
Safety 60%
96
Quality 40%
81
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
When it triggers w 12
20
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 Risky intent intent-offensive-security SKILL.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      description: Hunts for stolen-session and OAuth/PRT token replay (T1550.001) by correlating Microsoft Entra ID SigninLogs SessionId/UniqueTokenIdentifier fields and Okta System Log sso/session events
    • low Risky intent intent-offensive-security SKILL.md:39
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Post-incident hunting to scope SaaS lateral movement from a compromised identity
    • low Exfiltration net-credential-use SKILL.md:51
      Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
      curl -s -H "Authorization: SSWS $OKTA_API_TOKEN" \
      security skill
    • low Exfiltration net-credential-use SKILL.md:141
      Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
      curl -s -H "Authorization: SSWS $OKTA_API_TOKEN" \
      security skill

    Files scanned: 5. 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 56/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 20When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 32 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2707 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress
    • low 11 top-level sections: this looks like several domains in one skill

    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
    • -42 reference files, but SKILL.md never points to them: the model will not open them
    • +2Single-language instructions
    • +3Description length 413: enough signal without eating the budget
    • +4Structure: 20 headings
    • +3Step-by-step instructions: 32 items
    • +4Has examples (10 code blocks)
    • +3All 1 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.