Security Review
Security-focused review of an open-source pull request or diff. Use when the change touches authentication or authorization, cryptography, token or session handling, input parsing, deserialization, subprocess or shell invocation, file path construction, uploads and archive extraction, outbound HTTP built from user input (SSRF), permission and ACL logic, secrets and credential handling, or any code path where untrusted input reaches a sink. Also use when a reviewer explicitly asks for a security pass on a diff. Applies the suite's 10-point filter at a lowered floor of 7.5 and routes exploitable
Install
/plugin marketplace add priyank766/OpenSource-SKILLThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add priyank766/OpenSource-SKILL --skill security-reviewgit clone --depth 1 https://github.com/priyank766/OpenSource-SKILL.git /tmp/OpenSource-SKILL
mkdir -p ~/.claude/skills
cp -r /tmp/OpenSource-SKILL/skills/security-review ~/.claude/skills/security-reviewPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Security Review A specialised lens on [`pr-review`](https://github.com/priyank766/OpenSource-SKILL/blob/main/skills/pr-review/SKILL.md): the same diff, read only for the question *what can an attacker make this code do?* **Read first:** [`DETECTION-PLAYBOOK.md`](references/DETECTION-PLAYBOOK.md) · [`QUALITY-FILTER.md`](references/QUALITY-FILTER.md) · [`REVIEW-VOICE.md`](references/REVIEW-VOICE.md) > **Where the time goes.** Finding the flaw is the review. The playbook above is the > general flaw-hunting procedure; this file is the domain-specific lens on top of it. > Scoring and writing the comment are the last ten minutes, not the work. **Severity floor: 7.5** — lower than the suite default of 8.0. The cost of a miss is asymmetric. A false negative ships a CVE that outlives the release and lands on the maintainer as an unplanned patch cycle. A false positive costs the author five minutes to read and dismiss. When the two errors are that unequally priced, you lower the floor. The floor does not license volume. Everything under 9.0 is still batched into one comment. --- ## Why this exists Security findings are where generic AI review is at its worst. It flags `eval` in a comment string, misses the `os.path.join` two lines below that accepts a user-supplied filename, and then posts both with identical confidence. Maintainers learn to skim security feedback, which is exactly the feedback they cannot afford to skim.
Details
- Skill name
security-review- Repository
- priyank766/OpenSource-SKILL
- Path
skills/security-review/SKILL.md- License
- Apache-2.0
- Repo updated
- 6 August 2026
- Listed in
- karanb192/awesome-claude-skills
FAQ
What does the Security Review skill do?
Security-focused review of an open-source pull request or diff. Use when the change touches authentication or authorization, cryptography, token or session handling, input parsing, deserialization, subprocess or shell invocation, file path construction, uploads and archive extraction, outbound HTTP built from user input (SSRF), permission and ACL logic, secrets and credential handling, or any code path where untrusted input reaches a sink. Also use when a reviewer explicitly asks for a security pass on a diff. Applies the suite's 10-point filter at a lowered floor of 7.5 and routes exploitable
How do I install the Security Review skill?
Claude Code plugin: /plugin marketplace add priyank766/OpenSource-SKILL. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Security Review popular?
It lives in priyank766/OpenSource-SKILL, which has 1 GitHub stars and 0 forks, and is included in 1 curated skill list.
Related skills
API Compat Review
1priyank766/OpenSource-SKILL
Backward-compatibility review of changes to a project's public surface. Use when a diff changes exported function or type signatures, renames or removes public symbols, changes a default value, alters config keys, environment variables, or CLI flags, modifies an HTTP or wire format, migrates a database schema, changes exception or error types, touches plugin or extension hooks, or whenever a PR proposes a major-version bump. Establishes what the project actually promises, diffs the public surface between base and head with language-native tooling, classifies each change against a breaking-chan
Contributor Experience Review
1priyank766/OpenSource-SKILL
Review of a first-time or early-stage contributor's pull request, where the technical bar stays fixed but the sequencing, batching, and supplied context change. Use when GitHub labels the author a first-time contributor, when the PR comes from a newcomer to this repo, when it arrives via Hacktoberfest, GSoC, Outreachy, or a good-first-issue, when the change is technically close but procedurally messy (missing DCO, wrong base branch, unsigned commits, failing lint), or when the PR must be declined and the decline needs to not cost the project a future contributor. Applies a raised severity floo
Dependency Review
1priyank766/OpenSource-SKILL
Supply-chain review of dependency and CI changes in an open-source pull request. Use when a PR adds or bumps a dependency, changes a lockfile, introduces a build or postinstall script, edits a GitHub Actions workflow, changes a container base image, or when a bot-generated dependency bump needs human judgement before merge. Covers install-time code execution, package-identity and typosquat checks, artifact provenance, transitive footprint, license class, and workflow privilege changes. Ecosystem-agnostic — npm, PyPI, Go, Cargo, RubyGems, Composer, containers. Do NOT use for routine patch bumps
Active Directory Attacks
5lucaspmarie-a11y/claude-skills-vault
Provide comprehensive techniques for attacking Microsoft Active Directory environments. Covers reconnaissance, credential harvesting, Kerberos attacks, lateral movement, privilege escalation, and domain dominance for red team operations and penetration testing.
Arch Lens Security
5TalonT-Org/AutoSkillit
Create Security architecture diagram showing trust boundaries, validation layers, and process isolation. Security lens answering "Where are the trust boundaries?
Anti Reversing Techniques
5lucaspmarie-a11y/claude-skills-vault
AUTHORIZED USE ONLY: This skill contains dual-use security techniques. Before proceeding with any bypass or analysis: > 1.
Browse the most popular Claude skills, all security skills, or write your own with the skills generator.