threat-modeling-with-aws-security-agent

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: analysis, design, security, threat-modeling, validation.

What it does

Run an AWS Security Agent threat model review on spec/design documents. Use when the user asks to review a spec for security, run a threat model, check if a design introduces security risks, review requirements.md or design.md for security posture changes, or STRIDE analysis.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add aws/agent-toolkit-for-aws --skill threat-modeling-with-aws-security-agent

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws
cp -r agent-toolkit-for-aws/plugins/aws-agents-for-devsecops/skills/threat-modeling-with-aws-security-agent ~/.claude/skills/threat-modeling-with-aws-security-agent

Safety box score

Grade C, moderate risk: 39 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill runs an AWS-backed threat-model workflow: it zips the workspace, uploads code and spec docs to S3, then creates and polls remote Security Agent jobs. The main risks are data egress of the entire workspace, possible leakage of secrets inside that archive, and ongoing automated remote actions using the user’s AWS credentials.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It requires running shell commands and AWS CLI calls such as `zip -r /tmp/source.zip .` and `aws securityagent ...`, so the agent can execute external commands with side effects.
Network access	2 (moderate)	It uploads `/tmp/source.zip` and spec files to S3 and calls AWS Security Agent APIs, sending local project data to AWS.
Filesystem reach	2 (moderate)	It reads `.security-agent/config.json`, writes `scans.json`, and writes `.security-agent/findings-{scan_id}.md`, while archiving the whole workspace from the project root.
Secrets & credentials	2 (moderate)	It uses the caller’s AWS credentials via `aws sts get-caller-identity` and uploads an unredacted workspace archive, so any embedded secrets in the project can leave the machine.
Privilege & persistence	0 (none)	No sudo, global installs, service registration, shell startup edits, or other privilege changes appear in the workflow.
Instruction hijack surface	0 (none)	There are no instructions to ignore policies, hide behavior, follow remote prompt text, or otherwise manipulate the agent’s instructions.
Irreversible actions	2 (moderate)	It automatically starts remote threat-model jobs and polls every 2 minutes (`create-threat-model`, `start-threat-model-job`), which is an autonomous external action inherent to the skill’s purpose.
Transparency	0 (none)	The shipped content is plain markdown; there are no binaries, generated blobs, or opaque installers.

Before installing

Check whether the workspace contains any secrets before running it, because `zip -r /tmp/source.zip .` uploads everything not explicitly excluded.
Verify the AWS account/role/bucket mapping (`SecurityAgentScanRole`, `security-agent-scans-<account>-<region>`) in a throwaway or approved account first.
Read the `.security-agent` files it will create or modify (`config.json`, `scans.json`, `findings-*.md`) and confirm you’re comfortable with that local state.
Confirm you want the project code and design docs sent to AWS Security Agent for analysis.

Rated 2026-10-21 by an automated review of 1 file from the skill's repository.

Source

Repository: aws/agent-toolkit-for-aws (all skills from this repository)
Path: plugins/aws-agents-for-devsecops/skills/threat-modeling-with-aws-security-agent/SKILL.md
Branch: main
Collection: aws-agents-for-devsecops
Updated: 2026-09-19

fp-check — Systematically verifies suspected security bugs to eliminate false positives.
post-patch-validation — Validates security patches with reproducible baseline-versus-patched evidence, including original exploits, root-cause variants, behavior preservation.
principle-boundary-discipline — Apply when wiring validation, error handling, or framework adapters.
seo-technical — Technical SEO audit across 9 categories: crawlability, indexability, security, URL structure, mobile, Core Web Vitals, structured data, JavaScript rendering.
sharp-edges — Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes.
qa-expert — This skill should be used when establishing comprehensive QA testing processes for any software project.