SKILLEMALL.ai
GitHub ↗ RU Sign in

CC post-exploiting-microsoft-graph-with-graphrunner

Runs GraphRunner, a PowerShell post-exploitation toolset built on the Microsoft Graph API, to perform tenant recon, establish persistence (OAuth app injection, inbox rules), escalate privilege via group manipulation, and pillage mailboxes, SharePoint, and Teams data from a foothold Graph token. Use during authorized red-team engagements against Microsoft 365/Entra ID tenants once you hold a Graph token.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 5 files · 1 script body ≈ 2 399 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Runs GraphRunner, a PowerShell post-exploitation toolset built on the Microsoft Graph API, to perform tenant recon, establish persistence (OAuth app…

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

ProcedureGitHubPeople 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
C
85/100
safety, quality, tests
Safety 60%
93
Quality 40%
73
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
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 · 7

    ✓ No critical or high findings

    Medium and low: 7
    • low Risky intent intent-offensive-security references/api-reference.md:24
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | `Get-UpdatableGroups` | Groups the current principal can modify (privesc) |
    • low Risky intent intent-offensive-security references/api-reference.md:32
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## Privilege Escalation / Account Manipulation
    • low Risky intent intent-offensive-security SKILL.md:41
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Privilege Escalation** — `Get-UpdatableGroups`, `Invoke-AddGroupMember`, `Invoke-SecurityGroupCloner`, `Invoke-InviteGuest`.
    • low Risky intent intent-offensive-security SKILL.md:52
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - When demonstrating privilege escalation through updatable/dynamic groups.
    • low Risky intent intent-offensive-security SKILL.md:75
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Identify updatable groups and demonstrate privilege escalation.
    • low Risky intent intent-offensive-security SKILL.md:84
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | T1098.003 | Privilege Escalation | Account Manipulation: Additional Cloud Roles | Adding members to privileged/updatable groups |
    • low Risky intent intent-offensive-security SKILL.md:132
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Step 4: Privilege escalation via updatable groups

    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 51/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 6 mutating operations with no state check
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 27 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2399 tokens

    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
    • -42 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
    • +3Description length 406: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 27 items
    • +4Has examples (8 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.