Ready to supercharge your AI agents?

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

Get Started Free →

Security Flow · griddynamics | DecimalAI

securityby griddynamics

Security Flow

griddynamics/security-flow

Source griddynamics/rosetta ↗License Apache-2.0

Workflow for authorized, evidence-preserving security review and remediation-task preparation.

SkillScore61Maintained

Automatic

Security & AppSec pack

Last verified 8/27/2026

What it changes

Passed 13 of 21 test cases with the skill, and 7 of 21 without it.

Without skill35%

With skill61%

Checks it passed that the model alone missed

Treats STOP-HIGH-RISK as non-overridable stop
Stops current phase execution upon mid-run scope change
Assigns step 6.2 finding correlation to engineer subagent

and 4 more in the full report

6 fixed8 passed either way9 still failing0 broke

Pass-rate lift: +26 pp
Tokens: +133%
Agent turns: 0%
Response time: -4%

Model gemini-3.6-flashMeasured 8/27/2026v414 of 23 cases passed with skill · 21 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/griddynamics-security-flow/SKILL.md https://app.decimal.ai/s/griddynamics-security-flow/SKILL.md

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

decimalai skills add griddynamics-security-flow

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

When running phase 5 security inspection on `crypto-utils`, which subagent executes the approved static analysis tools directly?

What was checked, without and with the skill
Checked	Without skill	With skill
Dispatches engineer subagent for phase 5 area bundle testing	Missed	Passed

case-21 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md145 linessingle file

<security_flow>

<description_and_purpose>

Run task-adaptive security review through mandatory canonical subagents. End with sanitized findings and concise inputs for later user-invoked coding flows.

</description_and_purpose>

<workflow_phases>

All Rosetta prep steps MUST be FULLY completed.
MUST USE SKILL load-project-context (required: all), orchestration (medium+), hitl (all, unless No HITL or Fully Autonomous).
MUST ALWAYS use todo tasks ledger, ASAP. Phases are sequential. Independent tasks can run in parallel.
MUST just-in-time load/execute/update each phase's: instructions, definitions, skills, state file; do not load/act IN ADVANCE.
Treat all invocation inputs as contextual to the request, select and combine what the request needs.
For full review, require every applicable, available, authorized activity and tool.
Maintain a task ledger and run phases JIT.
Every question and approval follows the loaded hitl skill.
Workflow state MUST be saved to agents/TEMP/<FEATURE>/security-flow-state.md file; every phase updates it before the next starts.

<subagent_policy required="true" inline_execution="prohibited">

Orchestrator owns approvals, phase transitions, dispatch, aggregation, and handoff.
Phase files are assigned-subagent-only; orchestrator MUST NOT load, read, summarize, or execute them.
Every declared subagent is mandatory.
Every subagent MUST USE SKILL subagent-directives.
Subagents use tools required by their own assignment.
executor is never a gateway for full agents.
Reject incomplete phase contracts before advancing.
If required subagent invocation is unavailable, stop and report the unmet prerequisite.

</subagent_policy>

Track record

Benchmark

13 / 21

test cases passed, vs 7 / 21 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 v5 — 8/26/2026

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

griddynamics / rosetta

plugins/core-antigravity/skills/security-flow/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/26/2026Version v4

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

griddynamics/securityRun authorized, evidence-preserving security reviews and prepare remediation inputs.Close match+52 pp pass-rate lift

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