Ready to supercharge your AI agents?

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

Security (category index) — measured AI agent skill | DecimalAI

rshankras/security

NewSkillScoreMaintained

Security category index for Apple platforms. Routes to the privacy-manifests skill. General secure-storage/biometrics/ATS guidance was retired in the 2026 blind-test audit — current models cover it natively.

Securityby rshankras

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

Automatic

Security & AppSec pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/rshankras-security/SKILL.md

decimalai skills pull rshankras-security --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/rshankras-security/SKILL.md https://app.decimal.ai/s/rshankras-security/SKILL.md

Raw file: /s/rshankras-security/SKILL.md ↗ · machine-readable summary at /s/rshankras-security.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 2h ago

No — -100% lift-2% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✓→✗	▼ Worse	-18%	0%
case-01	✓→✓	＝ Same ✓	79%	0%
case-03	✓→✓	＝ Same ✓	35%	0%
case-04	✓→✓	＝ Same ✓	15%	0%
case-05	✓→✓	＝ Same ✓	5%	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

rshankras / claude-code-apple-skills

skills/security/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Security (category index)

General security guidance (Keychain patterns, biometric auth, certificate pinning, ATS) was removed from this library after the 2026-07 blind-test audit confirmed current models answer it correctly without a skill (tools/skill-audit/, Fable-verified coverage 0.86). What remains here is the material models get wrong or can't know.

Available Skills

privacy-manifests/

Privacy manifest audit — PrivacyInfo.xcprivacy format, required-reason APIs, App Tracking Transparency declarations, and App Store submission requirements.

Want to see if rshankras/security 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.