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 lm203688/aishield --skill aishield-scangit clone --depth 1 https://github.com/lm203688/aishieldWrote 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/lm203688/aishield/aishield-scan)<a href="https://agentmods.dev/skills/lm203688/aishield/aishield-scan"><img src="https://agentmods.dev/badge/skills/lm203688/aishield/aishield-scan/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/lm203688/aishield/aishield-scan"><img src="https://agentmods.dev/badge/skills/lm203688/aishield/aishield-scan.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 | $0.00067 | $0.00658 |
| Opus 5.5 | $0.00027 | $0.00263 |
| Sonnet 5.5 | $0.00013 | $0.00132 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
aishield-scan 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 26d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIShield scan
Use this skill whenever you are about to install, review, or ship an MCP server, an AI skill, a GPT definition, or a prompt file — or when a user asks "is this skill/plugin safe?".
AIShield is a static + offline-threat-intel scanner aligned to OWASP MCP Top 10
(2025 v0.1) and OWASP Agentic AI Top 10 (ASI01–ASI10). Its core invariant
is that it never spawns or executes any command found in the scanned config
(verifiable with python scripts/prove_isolation.py).
Prerequisites
Register the AIShield MCP server once:
{
"mcpServers": {
"aishield": { "command": "npx", "args": ["-y", "aishield-mcp-server"] }
}
}
Tools
| Tool | Use it for |
|---|---|
aishield_scan |
Full scan of a path, repo URL, or config blob → score, risk level, findings |
aishield_handshake |
Review an MCP config: npx -y risk, sensitive env vars, over-long tool descriptions |
aishield_prompt_check |
Detect prompt-injection / jailbreak patterns in prompts & instructions |
aishield_rug_pull |
Compare two versions of a tool description for silent (rug-pull) changes |
aishield_guardrail |
Check whether an agent config has adequate guardrails for its declared agency |
aishield_banned_words |
Flag policy-violating or risky terminology |
aishield_digest |
Compact trust digest — a few hundred bytes + a content fingerprint; same fingerprint = same verdict, so an agent need not re-pull the full report each turn |
Recommended workflow
- Before installing an untrusted skill/MCP server, call
aishield_scanon its source path or repo URL. Treatrisk_level: high|criticalas a stop sign. - For an MCP config, call
aishield_handshakeand review every flagged field. - When a tool's description changes between versions, call
aishield_rug_pullto catch a rug pull (benign v1 → malicious v2). - Report findings to the user with the file, line, rule id and evidence — never just a score.
Notes
- Scanning is local: source code never leaves the machine.
- Optional live CVE enrichment (OSV.dev) is off by default; keep it off for privacy-sensitive or air-gapped work.
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.
- 26d ago Changed · +1 lines dacc237355b6
- 1mo ago First seen · 59 lines · 67 tokens per session scan A 9add15a43a9a
aishield-scan is a skill published in the GitHub repository lm203688/aishield (2 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 658 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
polygraph
Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
apitap
ApiTap gives AI agents cheap access to web data through three layers.