Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aeonfun/aeonnpx agentmods add skills/aeonfun/aeon/vuln-scannerWrote 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/aeonfun/aeon/vuln-scanner)<a href="https://agentmods.dev/skills/aeonfun/aeon/vuln-scanner"><img src="https://agentmods.dev/badge/skills/aeonfun/aeon/vuln-scanner.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 11 findings, up to high
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 →
- high Prompt Injection · line 20 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Supply Chain · line 108 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Supply Chain · line 1057 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Prompt Injection · line 588 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 908 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium MCP Rug Pull · line 350 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Data Exfiltration · line 743 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 966 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 966 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- low Supply Chain · line 110 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- low Supply Chain · line 110 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00039 | $0.19308 |
| Opus 5 | $0.00019 | $0.09654 |
| Sonnet 5 | $0.00008 | $0.03862 |
| Haiku 4.5 | $0.00004 | $0.01931 |
Grade B, and why
vuln-scanner scanned grade B with 2 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 2d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
network is open, but `pip install` / `curl | sh` / `tar` are **not** on the in-run Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
network is open, but `pip install` / `curl | sh` / `tar` are **not** on the in-run Copies of this mod
1 near-identical copy found in the catalogue:
- vuln-scanner — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 1,135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
${var} — Action selector, shaped
[<action>][:<owner/repo>]. Empty or a bareowner/repo→ scan arm (audit that repo, or auto-select a trending one).resubmit/resubmit:owner/repo→ re-submit arm (probe the security watchlist for repos that just enabled PVR and submit any queued advisory).disclose/
- `` → scan, auto-select from trending
openai/whisper→ scanopenai/whisperresubmit→ probe the whole watchlist and re-submit what flippedresubmit:vercel/next.js→ probe just that repo (one-off)disclose(aliaspoc-smoke→ exercise the PoC gate against a benign real Base fork (no audit or disclosure)
Today is ${today}. Read memory/MEMORY.md and the last 30 days of memory/logs/ before starting.
Why this skill exists
This is the write / action arm of the vuln-disclosure loop — one skill covering the full responsible-disclosure lifecycle:
- Scan — a security scanner that dumps unpatched vulnerabilities into public PRs is a zero-day publisher, not a helper. This skill matches industry practice: Private Vulnerability Reporting (PVR) for code flaws, public PRs only for dependency CVEs that are already public. Bad disclosure burns credibility and puts users at risk.
- Re-submit — when a scan finds a HIGH/CRITICAL issue in a repo with no PVR, no
SECURITY.md, and no reachable contact, it has no safe channel — so it logs the finding as"channel": "skipped"inmemory/vuln-scanned.jsonand stages a watchlist row. Without a weekly probe those findings silently age until the responsible-disclosure window closes. The re-submit arm closes that loop. - Disclose — when the only responsible path is a private email to the maintainer, drafts sit in
memory/pending-disclosures/withstatus: pending-operator-send, waiting for a human. The disclose arm finds drafts explicitly armed for auto-send, composes the email, and sends it in-run (Resend via./secretcurl) behind a set of fail-closed caps — the send is the arm's final action.
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.
- 2d ago Changed · +44 lines 1328de6f3288
- 3d ago First seen · 1,091 lines · 39 tokens per session scan B b17491de609e
vuln-scanner is a skill published in the GitHub repository aeonfun/aeon (716 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 19,308 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
flowcraft-config
Author, validate, and troubleshoot complete FlowCraft deployment configuration (deploy.yaml with the runtime section, inference/workspace/sandbox/tool sub-documents, core/memory contracts, and graph JSON node wiring). Use when writing or reviewing FlowCraft configs, assembling an agent deployment, adding…
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
unit-converter
Converts values between metric and imperial units, using the project's agreed factors.
explore
Explore the codebase and summarize how the project is wired.
flow-define
Multi-AI requirements scoping using Codex and Gemini CLIs (Double Diamond Define phase). Use when: AUTOMATICALLY ACTIVATE when user requests clarification or scoping:. "define the requirements for X". "clarify the scope of Y".
flow-develop
Multi-AI implementation using Codex and Gemini CLIs (Double Diamond Develop phase). Use when: AUTOMATICALLY ACTIVATE when user requests building or implementation:. "build X" or "implement Y" or "create Z". "develop a feature for X".