Retenta has not executed this skill.
Evidence record · captured 2026-10-11
Security Threat Model
Produces a repository-grounded AppSec threat model in Markdown: the agent extracts components, data stores and integrations from the code, enumerates trust boundaries, assets, attacker capabilities and abuse paths, and proposes mitigations, anchoring every claim to repo evidence and keeping assumptions explicit. It only triggers on an explicit threat-modeling request and follows a bundled output template.
Community publisherUnverifiedSource reviewedBehavior not tested
Source review
Editorial assessment
This is a source-only assessment. It does not claim runtime or security testing.
What it does
Has the agent build an AppSec threat model from the repository itself, with every architectural claim anchored to a file path. It stops to confirm deployment and exposure assumptions with the user before ranking threats.
Best for
- A first threat model for a service or library before a security review or launch
- Deciding where manual security review time should go in an unfamiliar codebase
- Documenting trust boundaries and attacker capabilities for a specific subpath
Strengths in the source
- Requires repository evidence (a path plus a symbol, config key or snippet) for components and controls, and explicit assumptions where evidence is missing.
- Pauses after drafting to ask 1 to 3 targeted questions about deployment, exposure, auth and data sensitivity, and marks recommendations conditional if they go unanswered.
- Separates runtime behavior from CI, build and test code, and lists attacker non-capabilities to keep severity from inflating.
- Ends with a checklist that every entry point and trust boundary is covered, and writes a fixed-format Markdown file with a Mermaid diagram.
Limitations
- Produces a document and recommendations, not tested findings; it does not run scanners or verify that an abuse path works.
- Writes a <repo>-threat-model.md file into the working directory, which can end up in version control if not handled.
- Comes from openai/skills, which its README marks as deprecated in favor of a newer repository, so this copy may stop receiving updates.
When not to use it
- General architecture summaries or code review, which the skill itself says it should not trigger for
- When you need concrete vulnerabilities found and confirmed rather than a prioritized model
Reviewed by Retenta editorial on 2026-10-11; scope: source only.
Files included in this review
skills/.curated/security-threat-model/SKILL.md
Evidence and boundaries
The skill folder bundles no executable scripts. Retenta has not run a security scan.
- Pinned publisher source
- skills/.curated/security-threat-model/SKILL.md
- Revision
- 49f948faa9258a0c61caceaf225e179651397431
- License evidence
- Apache-2.0Retenta preserves the license text captured with this immutable upstream snapshot; no independent legal or security review is claimed.
- Last source change
- 2026-02-02
- Independent verification
- Published by OpenAI, which does not own the product this skill covers. Not independently verified.
- Upstream repository
- Open publisher repository
Compatibility
OpenAI Codex ($skill-installer)
documentedNamed in the upstream skill or repository documentation; not tested by Retenta.
Requirements and access
- None required
Referenced tools
No named tool is required by the reviewed SKILL.md.
Install from the source
Clones the current default branch, which may be newer than the reviewed revision 49f948f. The destination shown is Claude Code's personal skills folder; other agents read the same folder from their own skills directory.
View the SKILL.md at its source Verify the publisher's install documentationInstall the full skill folder
git clone --depth 1 https://github.com/openai/skills.git
cp -R skills/skills/.curated/security-threat-model ~/.claude/skills/security-threat-modelThyme RAG Capsules
Make this skill’s state durable, governed, and portable.
A Retenta capsule lets agents recall prior work, append provenance-stamped progress, and carry the memory to the next run.