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 akanthed/SecureAI-Scan --skill sdk-provider-docsgit clone --depth 1 https://github.com/akanthed/SecureAI-ScanWrote 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/akanthed/secureai-scan/sdk-provider-docs)<a href="https://agentmods.dev/skills/akanthed/secureai-scan/sdk-provider-docs"><img src="https://agentmods.dev/badge/skills/akanthed/secureai-scan/sdk-provider-docs/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/akanthed/secureai-scan/sdk-provider-docs"><img src="https://agentmods.dev/badge/skills/akanthed/secureai-scan/sdk-provider-docs.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 | $0.00019 | $0.00811 |
| Opus 5 | $0.00010 | $0.00405 |
| Sonnet 5 | $0.00004 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
sdk-provider-docs 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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Package layout
-
layout detail 1
-
layout detail 2
-
layout detail 3
-
layout detail 4
-
layout detail 5
-
layout detail 6
-
layout detail 7
-
layout detail 8
-
layout detail 9
-
layout detail 10
-
layout detail 11
-
layout detail 12
-
layout detail 13
-
layout detail 14
-
layout detail 15
-
layout detail 16
-
layout detail 17
-
layout detail 18
-
layout detail 19
-
layout detail 20
-
dependency on
@ai-sdk/provider-utilsviaworkspace:*when using sandbox/auth utilities -
dependency on
@ai-sdk/harnessviaworkspace:* -
build detail 1
-
build detail 2
-
build detail 3
-
build detail 4
-
build detail 5
-
build detail 6
-
build detail 7
-
build detail 8
-
build detail 9
-
build detail 10
-
build detail 11
-
build detail 12
-
build detail 13
-
build detail 14
-
build detail 15
-
build detail 16
-
build detail 17
-
build detail 18
-
build detail 19
-
build detail 20
-
build detail 21
-
build detail 22
-
build detail 23
-
build detail 24
-
build detail 25
-
build detail 26
-
build detail 27
-
build detail 28
-
build detail 29
-
build detail 30
Security Best Practices
-
Never use
JSON.parsedirectly - usesafeParseJSONfrom@ai-sdk/provider-utils -
Load API keys securely using
loadApiKeyfrom@ai-sdk/provider-utils -
Validate all API responses against schemas
-
testing detail 1
-
testing detail 2
-
testing detail 3
-
testing detail 4
-
testing detail 5
-
testing detail 6
-
testing detail 7
-
testing detail 8
-
testing detail 9
-
testing detail 10
-
testing detail 11
-
testing detail 12
-
testing detail 13
-
testing detail 14
-
testing detail 15
-
testing detail 16
-
testing detail 17
-
testing detail 18
-
testing detail 19
-
testing detail 20
-
testing detail 21
-
testing detail 22
-
testing detail 23
-
testing detail 24
-
testing detail 25
-
testing detail 26
-
testing detail 27
-
testing detail 28
-
testing detail 29
-
testing detail 30
-
testing detail 31
-
testing detail 32
-
testing detail 33
-
testing detail 34
-
testing detail 35
-
testing detail 36
-
testing detail 37
-
testing detail 38
-
testing detail 39
-
testing detail 40
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.
- 9d ago First seen · 134 lines · 19 tokens per session scan A d39d1f8811f7
sdk-provider-docs is a skill published in the GitHub repository akanthed/SecureAI-Scan (19 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 811 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
AI & LLM Security
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments.
llm-prompt-injection
Use when testing an authorized LLM application for prompt injection, system-prompt exposure, unsafe tool use, or RAG data-boundary failures.
testing-prompt-injection-in-rag-pipelines
Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.
prompt-injection
Tests LLM applications for prompt injection vulnerabilities per OWASP LLM01:2025. Covers direct injection (user input manipulating model behavior) and indirect injection (external content containing hidden instructions). Auto-invoked when reviewing LLM applications that process external content, build RAG pipelines…
assay
Pre-install security advisor. Activate when the user mentions installing a Claude Code plugin, MCP server, or any third-party agent tool. Offer to run an Assay scan against the target before they install.
llm-prompt-injection
Identify and exploit vulnerabilities in Applications integrating Large Language Models (LLMs). Prompt Injection involves crafting inputs that override the original system instructions provided by the developer, allowing an attacker to exfiltrate data, bypass restrictions, or manipulate the AI's output logic.