Ready to supercharge your AI agents?

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

Security Review — measured AI agent skill | DecimalAI

hmbown/security-review

SkillScore86Maintained

Review trust boundaries, auth/authz, injection, secrets, filesystem/network exposure, dependencies, and exploitability without pretending a shallow lint is an audit.

by hmbown

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Security & AppSec pack

decimalai skills pull hmbown-security-review

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/hmbown-security-review/SKILL.md

Raw file: /s/hmbown-security-review/SKILL.md ↗ · machine-readable summary at /s/hmbown-security-review.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3d ago

Yes — +9% lift+10% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-11	✗→✓	▲ Improved	-3%	0%
case-14	✗→✓	▲ Improved	-6%	0%
case-07	✓→✓	＝ Same ✓	-27%	0%
case-08	✓→✓	＝ Same ✓	-28%	0%
case-15	✓→✓	＝ Same ✓	83%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

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

hmbown / codewhale

crates/tui/assets/skills/security-review/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Security Review

When to use

Use when looking for vulnerabilities, auth holes, secret leaks, or unsafe trust boundaries.

Non-goals

This is not a formal audit certificate.
Do not claim exploitability without evidence.

Workflow

Map trust boundaries and entry points.
Check auth/authz, injection, secrets, FS/network exposure, deps.
Rank findings by exploitability and impact.
Recommend fixes and verification steps.

Want to see if hmbown/security-review would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.