SkillSpector is a security scanner that examines AI agent skills and related files for malicious behavior, vulnerabilities, and other installation risks. It is used to assess skills for agents such as Claude Code, Codex CLI, Gemini CLI, and MCP-based tools before they are installed, while the catalogue includes skills for using the scanner.
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 agentmods add skills/nvidia/skillspector/sqp2_cleannpx skills add NVIDIA/SkillSpector --skill sqp2_cleangit clone --depth 1 https://github.com/NVIDIA/SkillSpectorWrote 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/nvidia/skillspector/sqp2_clean)<a href="https://agentmods.dev/skills/nvidia/skillspector/sqp2_clean"><img src="https://agentmods.dev/badge/skills/nvidia/skillspector/sqp2_clean.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00102 |
| Opus 5 | $0.00006 | $0.00051 |
| Sonnet 5 | $0.00003 | $0.00020 |
| Haiku 4.5 | $0.00001 | $0.00010 |
Grade A, and why
deploy-service 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 6d 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.
What it actually says
Deploy Service
Purpose
Automates deployment to the staging environment by running shell scripts.
Warnings
- This skill executes shell commands on your behalf.
- It will restart running services, which causes brief downtime.
- Review the generated deploy script before confirming execution.
Usage
Provide the service name and target environment. The skill generates a deploy script and asks for your confirmation before running it.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 22 lines · 13 tokens per session scan A 82d9b08914c8
deploy-service is a skill published in the GitHub repository NVIDIA/SkillSpector (16,312 stars, last pushed 4d ago), licensed Apache-2.0. It adds 13 tokens to every session and 102 once invoked, about $0.0001 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
research-new-attack-classes
Keep AVE current with the real threat landscape. This skill researches agentic AI / MCP attack classes from primary sources, benchmarks each against the existing AVE record set, and for every class decides one of three outcomes: ALREADY COVERED, VARIANT OF EXISTING, or NEW CLASS.
tdd
For this repo, TDD means: fixtures first, then rule, then record validation.
setup-ave-skills
Skill "setup-ave-skills" from aveproject/ave, covering setup-ave-skills, install matt pocock's skills and key context.
grill-with-docs
Grill before defining a vulnerability class. No record until complete.
diagnose
Repro: run the rule against the negative fixture in isolation. Minimize: trim the negative fixture to the smallest triggering line. Hypothesize: which pattern/condition is too broad? Fix: tighten the rule. Re-run both fixtures.
handoff
End: docs/agents/handoffs/YYYY-MM-DD-HHMM.md Start: read most recent, run python scripts/validaterecords.py.