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 UnboundCompute/security-agent-skills --skill auditing-ai-agent-permissionsgit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/unboundcompute/security-agent-skills/auditing-ai-agent-permissions)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-ai-agent-permissions"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ai-agent-permissions/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/unboundcompute/security-agent-skills/auditing-ai-agent-permissions"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ai-agent-permissions.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 | $0.00116 | $0.01500 |
| Opus 5 | $0.00058 | $0.00750 |
| Sonnet 5 | $0.00023 | $0.00300 |
| Haiku 4.5 | $0.00012 | $0.00150 |
Grade A, and why
auditing-ai-agent-permissions 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing AI agent permissions: agency is what's left when the prompt defense fails
Prompt-level defenses are probabilistic and bypassable. What remains after an injection succeeds is what the agent is permitted to do, so the durable control is the permission set, not the model's judgment. Auditing agency means comparing every capability the agent holds against what its task actually requires, and gating the actions that cannot be undone.
When to use
- You are granting an agent a new tool, scope, credential, or autonomous action.
- You are reviewing an agent's permission and egress posture.
- You are deciding which actions require human approval and which can run freely.
- You are scoping a code interpreter or shell an agent can drive.
Scope check
Audit agents and systems you own or are authorized to test. Do not exercise destructive or irreversible actions against systems you do not control. If you can't name the authorization, stop.
The loop
-
Diff granted capability against required capability. List every tool, scope, credential, and autonomous action the agent has. Beside each, write what the task actually needs. The gap is excessive agency: a summarizer with delete rights, a read task holding a write token, a support bot that can issue uncapped refunds.
-
Classify actions by reversibility and blast radius. Mark each action reversible or irreversible, low or high impact. Irreversible or high-impact actions (deleting data, sending money or messages externally, changing access, deploying) are the set that needs a gate, no matter how aligned the model seems.
-
Check human-in-the-loop on the dangerous set. For each irreversible or high-impact action, is there an approval gate, or does the agent execute alone? A gate the agent can auto-approve, pre-approve, or that fires after the effect does not count. The test is whether a human authorizes before the irreversible step.
-
Test credential blast radius. Does a credential grant more than the tool needs: a broad API key, an admin role, a token valid for other systems? If the agent is compromised through injection, its credentials are the blast radius. Scope each token to the minimum the specific tool requires.
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 · 127 lines · 116 tokens per session scan A 28e145fe926a
auditing-ai-agent-permissions is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 1,500 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-langgraph
Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.