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 andrewsrigom/agent-skills --skill security-input-validation-and-dangerous-sinksgit clone --depth 1 https://github.com/andrewsrigom/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/andrewsrigom/agent-skills/security-input-validation-and-dangerous-sinks)<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/security-input-validation-and-dangerous-sinks"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/security-input-validation-and-dangerous-sinks/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/andrewsrigom/agent-skills/security-input-validation-and-dangerous-sinks"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/security-input-validation-and-dangerous-sinks.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 | $0.00051 | $0.00474 |
| Opus 5 | $0.00026 | $0.00237 |
| Sonnet 5 | $0.00010 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
security-input-validation-and-dangerous-sinks 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 10d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Input Validation And Dangerous Sinks
Use this skill when the risk comes from attacker-controlled input flowing into a dangerous sink.
Scope
- input validation
- normalization
- parameterized database access
- HTML and output-context encoding
- shell, path, redirect, and URL sink safety
Default path
- Name the untrusted input source.
- Name the dangerous sink it can reach.
- Validate and normalize input once near entry.
- Use sink-specific protection:
- parameterized queries for SQL
- context-appropriate escaping or encoding for HTML
- path allowlists or fixed roots for filesystem access
- no shell interpolation for command execution
- redirect allowlists for outbound navigation
- Keep raw attacker input away from privileged sinks when possible.
When to deviate
- Use richer schema validation only when the domain actually needs structured coercion or refinement.
- Allow limited rich text only with a deliberate sanitization and rendering boundary.
- Use raw input logs sparingly and only with redaction when sensitive data may be present.
Guardrails
- Validation is not generic string cleaning.
- Protection must match the sink, not just the input type.
- Normalize once; avoid multiple inconsistent parsing paths.
- Prefer avoiding dangerous sinks entirely when the feature design allows it.
Avoid
- “sanitize everything” with no sink model
- string-concatenated SQL
- trusting file paths or redirect targets from raw input
- assuming one HTML sanitizer solves shell, SQL, and URL problems too
Verification checklist
- source input is named
- dangerous sink is named
- validation and normalization happen once
- sink-specific protection is used
- raw attacker input is not flowing unchecked into privileged operations
Output Shape
When answering with this skill, prefer:
- untrusted source
- dangerous sink
- required validation
- required sink-specific protection
- main exploit path if left unchanged
References
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.
- 10d ago First seen · 72 lines · 51 tokens per session scan A 24f938d348ca
security-input-validation-and-dangerous-sinks is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 474 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…