Borrowing it
Nothing to install: this file belongs to SCStelz/security-investigator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SCStelz/security-investigator/main/.github/skills/ai-agent-activity/SKILL.mdgit clone --depth 1 https://github.com/SCStelz/security-investigatorWrote 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/scstelz/security-investigator/ai-agent-activity)<a href="https://agentmods.dev/skills/scstelz/security-investigator/ai-agent-activity"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/ai-agent-activity/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/scstelz/security-investigator/ai-agent-activity"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/ai-agent-activity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 305 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium System Prompt Leakage · line 407 Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
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 | $0.00194 | $0.17130 |
| Opus 5 | $0.00097 | $0.08565 |
| Sonnet 5 | $0.00039 | $0.03426 |
| Haiku 4.5 | $0.00019 | $0.01713 |
Grade A, and why
ai-agent-activity scanned grade A with 0 findings 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 910 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Activity — Instructions
Purpose
This skill reports the runtime activity of AI agents built on Agent 365 / Copilot Studio / Microsoft 365 Copilot / Work IQ across a tenant — who invoked which agents, what tools and connectors ran, over which channels, with what token/inference usage, and what the content-safety layer (Prompt Shield jailbreak / XPIA) caught.
It answers "what are the agents actually doing?" — the behavioral counterpart to the configuration-focused ai-agent-posture skill.
ai-agent-posture (config) |
ai-agent-activity (this skill — runtime) |
|
|---|---|---|
| Question | How are agents configured? (access, tools declared, data sources, credentials) | What are agents doing? (prompts, tool calls, users, channels, safety flags) |
| Primary table | AgentsInfo (Advanced Hunting) |
UnifiedAgentObservability (Data Lake) or CloudAppEvents (Defender) |
| Time model | Point-in-time config snapshots | Event stream over a lookback window |
| Use together | Posture flags a broadly-accessible, email-capable agent | Activity shows whether that agent is actually used, by whom, and whether it was jailbroken |
Use them together: run ai-agent-posture to find the risky configurations, then run this skill to see which of those agents are active-and-dangerous at runtime.
References:
- Query library (all validated KQL):
queries/cloud/agent365_observability.md— this skill references those queries rather than duplicating them. It contains the Plane A + Plane B equivalents, theRawEventData↔UnifiedAgentObservabilityfield crosswalk, and the Defender-parity matrix. - Security for AI native alerts (companion signal): see Core Queries C12 below — for tenants with Microsoft Defender's Security for AI capability enabled, covers the native
AlertInfo/AlertEvidencealert family (ServiceSource == "Security for AI": malicious URL, obfuscated/encoded payload, and other runtime-threat alerts) that is broader than, and complementary to, the Prompt Shield jailbreak/XPIA signal in §7. - Agent 365 Observability SDK
- Agent 365 observability concepts
- Detect and investigate threats to AI agents using Microsoft Defender (Preview)
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.
- 11d ago First seen · 910 lines · 194 tokens per session scan A f983d6d091c4
ai-agent-activity is a skill published in the GitHub repository SCStelz/security-investigator (245 stars, last pushed 3d ago), licensed MIT. It adds 194 tokens to every session and 17,130 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…