Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Input Validation · archive228 | DecimalAI

securityby archive228

Input Validation

archive228/input-validation

Source archive228/loopkit ↗License MIT

Validate and constrain untrusted input at the boundary.

SkillScore100Maintained

Automatic

Security & AppSec pack

Last verified 8/16/2026

What it changes

Passed 24 of 24 test cases with the skill, and 23 of 24 without it.

Without skill96%

With skill100%

Checks it passed that the model alone missed

Re-validate formatted component strings after parsing them.

1 fixed23 passed either way0 still failing0 broke

Pass-rate lift: +4 pp
Tokens: -22%
Agent turns: 0%
Response time: -29%

Model gemini-3.6-flashMeasured 8/16/2026v124 of 24 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/archive228-input-validation/SKILL.md https://app.decimal.ai/s/archive228-input-validation/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add archive228-input-validation, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/archive228-input-validation/ and pins it in .decimal/skills.lock

decimalai skills add archive228-input-validation

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/archive228-input-validation/SKILL.md https://app.decimal.ai/s/archive228-input-validation/SKILL.md

Raw file: /s/archive228-input-validation/SKILL.md ↗ · machine-readable summary at /s/archive228-input-validation.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

An API route accepts date ranges formatted as `2026-01-01..2026-01-31`. The handler splits the string on `..` and passes the resulting sub-strings directly into database date filters. How should these split string components be handled before execution?

What was checked, without and with the skill
Checked	Without skill	With skill
Re-validate formatted component strings after parsing them.	Missed	Passed

case-18 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md8 linessingle file

Input Validation

Validate at the edge, before the data touches logic or storage.

Schema — type, required fields, allowed values. Reject unknown fields rather than ignoring them.
Bounds — string length, number ranges, array size. An unbounded input is a DoS and a memory bomb.
Format — emails, UUIDs, dates parsed and re-validated, not trusted as strings.
Files — size limit, type allowlist (check content, not just extension), no path traversal in names.
Reject with a clear 4xx and a message that says what's wrong — without leaking internals. Never trust "it comes from our own frontend". The request can come from anywhere.

Track record

Benchmark

24 / 24

test cases passed, vs 23 / 24 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

archive228 / loopkit

skills/input-validation/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Input Validation

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills