Ready to supercharge your AI agents?

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

Security Audit · josstei | DecimalAI

securityby josstei

Security Audit

josstei/security-audit

Source josstei/maestro-orchestrate ↗License Apache-2.0

Run a Maestro-style security assessment for authentication, authorization, data exposure, secret handling, and exploitability risks

NewMaintained

Automatic

Security & AppSec pack

Last verified 8/19/2026

What it changes

Passed 6 of 18 test cases with the skill, and 12 of 18 without it.

Without skill67%

With skill33%

Checks it passed that the model alone missed

The response evaluates access control logic in relevant code paths.
The response checks for OWASP Top 10 flaws including SQL injection.
The response reviews third-party dependencies for high-risk vulnerabilities alongside custom code.

and 1 more in the full report

2 fixed2 passed either way14 still failing4 broke

Pass-rate lift: -33 pp
Tokens: +14%
Agent turns: 0%
Response time: -2%

Model gemini-3.6-flashMeasured 8/19/2026v24 of 22 cases passed with skill · 18 comparable

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/josstei-security-audit/SKILL.md https://app.decimal.ai/s/josstei-security-audit/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add josstei-security-audit, 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/josstei-security-audit/ and pins it in .decimal/skills.lock

decimalai skills add josstei-security-audit

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

We found an unauthenticated endpoint in `src/api/user.py` returning user profile data. Can you quickly write a patch using Flask-Login decorators without inspecting database queries or auth middleware?

What was checked, without and with the skill
Checked	Without skill	With skill
The response traces trust boundaries and data exposure paths across auth flows before recommending fixes.	Missed	Passed
The response evaluates access control logic in relevant code paths.	Missed	Passed

case-06 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md11 linessingle file

Read ../../references/runtime-guide.md. Call get_skill_content with resources: ["architecture", "delegation"]. Call get_agent with agents: ["security-engineer"].

Workflow

Define the audit scope from the user request and relevant code paths
Trace trust boundaries, auth flows, secret handling, and data exposure paths
Review for exploitable flaws, unsafe defaults, OWASP Top 10 vulnerabilities, and high-risk dependencies
Classify findings by severity (CVSS-aligned) with file references and exploitability assessment
Provide remediation guidance with the highest-risk issues first

Track record

Benchmark

6 / 18

test cases passed, vs 12 / 18 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

josstei / maestro-orchestrate

claude/skills/security-audit/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v2

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