Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add adriannoes/awesome-agentic-ai --skill hunt-sharepointgit clone --depth 1 https://github.com/adriannoes/awesome-agentic-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/hunt-sharepoint)<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/hunt-sharepoint"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/hunt-sharepoint/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/hunt-sharepoint"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/hunt-sharepoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00170 | $0.07877 |
| Opus 5 | $0.00085 | $0.03939 |
| Sonnet 5 | $0.00034 | $0.01575 |
| Haiku 4.5 | $0.00017 | $0.00788 |
Grade A, and why
hunt-sharepoint scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sk "https://target.example/_vti_inf.html" This is a copy
89% identical to hunt-sharepoint — 79 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crown Jewel Targets
SharePoint Server (on-prem) is one of the richest enterprise attack surfaces in 2025-2026 bug bounty / red-team work. Three forces converge:
- End-of-life unpatched code paths. SharePoint Server 2013 reached extended-support EoL on 2023-04-11 (final build
15.0.5545.1000/ KB5002381). Every SharePoint CVE published after that date is permanently unpatched on SP2013 farms. SP2016 reaches EoL 2026-07-14; SP2019 reaches EoL 2026-07-14 (next 2 months as of May 2026); only SP Subscription Edition is currently in active support. - CVE-2025-53770 / 53771 "ToolShell" — July 2025 emergency-out-of-band patch chain for SPE / SP2019 / SP2016. The vulnerable code path (anonymous
/_layouts/15/ToolPane.aspx?DisplayMode=Edit+ anonymous__REQUESTDIGEST+ unencrypted ViewState) is present in SP2013 too and will never receive a fix. - Custom branded login pages forget legacy SOAP login.
/_vti_bin/Authentication.asmxwith theLoginSOAP op is the SharePoint equivalent of WordPress XMLRPC bypass — accepts native Forms credentials anonymously with no rate limit on most farms even when the branded UI has lockout.
Highest-value SharePoint targets:
- SP2013 farms still on the public internet — every CVE since April 2023 is unpatched. Critical-severity findings.
- Dealer / partner / supplier portals built on SharePoint by enterprise integrators (German VW group, a enterprise system integrator, etc.) — high-impact business data, often nested inside corporate AD trees.
- SharePoint farms with anonymous Forms-auth zones — Authentication.asmx becomes anonymously brute-forceable.
- SharePoint inside corporate AD parent forests — NTLM Type-2 leak (see
hunt-ntlm-info) discloses the parent forest membership. - Telerik-integrated SharePoint installations — additional deserialization sinks on top of SP's own.
Asset types that pay most: internet-reachable SP Server (any version) > SP Online with custom solutions hooks > intranet SP only after VPN compromise.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 438 lines · 170 tokens per session scan A 3717a514c5af
hunt-sharepoint is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 14d ago), licensed MIT. It adds 170 tokens to every session and 7,877 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 89% identical to hunt-sharepoint, differing in 79 lines, and is treated as a copy.
Other skills, from other repositories
kotlin-ktor-patterns
Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.
goframe-v2
GoFrame development skill. TRIGGER when writing/modifying Go files, implementing services, creating APIs, or database operations. DO NOT TRIGGER for frontend/shell scripts.
java-coding-standards
Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.
backend-builder
A backend implementation role for Codex Project Autopilot, a workflow that coordinates project work. It builds the server-side logic and connects it to integrations according to an approved plan.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
api-design
Use this skill when designing, reviewing, or refactoring REST APIs in WrongStack. Triggers: user says "API", "endpoint", "REST", "request", "response", "JSON", "HTTP", "status code", "pagination", "query params", "request body".