Skip to content
Skills Library
Security · Review & audit

teamsecure

/teamsecure

Use when running an adversarial security review of a code change — a GitHub PR, a local working-tree diff, or an explicit file list — and when wiring security review into a teamimplement run. Use when asked to security-review, audit, or vulnerability-assess freshly written or proposed code.

Licence
MIT
Last repository change
26.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
4
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when running an adversarial security review of a code change — a GitHub PR, a local working-tree diff, or an explicit file list — and when wiring security review into a teamimplement run. Use when asked to security-review, audit, or vulnerability-assess freshly written or proposed code.

Original author description

Use when running an adversarial security review of a code change — a GitHub PR, a local working-tree diff, or an explicit file list — and when wiring security review into a teamimplement run. Use when asked to security-review, audit, or vulnerability-assess freshly written or proposed code.

How it works

  1. When to use
  2. Input modes
  3. Pipeline (overview — full detail in references/pipeline.md)
  4. Non-negotiables
  5. Output
  6. Agents
Original SKILL.md headings · 47 lines, 440 words
SKILL.md preview
---
name: teamsecure
description: Use when running an adversarial security review of a code change — a GitHub PR, a local working-tree diff, or an explicit file list — and when wiring security review into a teamimplement run. Use when asked to security-review, audit, or vulnerability-assess freshly written or proposed code.
---

# teamsecure

Orchestrate an adversarial security review of a code change. You drive two isolated
agents — a **paranoid finder** and a **critical validator** — then verify the survivors
yourself and write a structured findings file.

You are the **orchestrator**. You spawn the agents, enforce the gates, and own the final
verification. You do not perform the first-pass find or the validation yourself; those are
the agents' jobs.

**The canonical, authoritative procedure is in `references/pipeline.md`.** Read it and
follow it exactly. This file is the entry point and the overview; `pipeline.md` is the
source of truth (it is the same procedure `teamimplement` cites, so the two stay in sync).

## When to use
- A PR needs a security review.
- A local, uncommitted change needs a security review (e.g. driven by `teamimplement`).
- An explicit set of changed files needs a security review.

## Input modes
The argument selects the scope:
- `<PR number>` → review a GitHub PR. Resolve the repo dynamically; never hardcode it.
- `--diff` → review the local working-tree / uncommitted changes (`git diff`).
- `--files <a> <b> ...` → review the explicit file list.

## Pipeline (overview — full detail in references/pipeline.md)
1. **Resolve scope** and build the authoritative changed-file list.
2. **Paranoid pass** — spawn `security-paranoid-reviewer`; receive coverage inventory + findings.
3. **Coverage gate** — verify coverage is complete (see `references/coverage-inventory.md`); re-dispatch the finder if not. Do not advance with incomplete coverage.
4. **Critical pass** — spawn `security-critical-reviewer` with the **findings list only** (context isolation is mandatory). Receive verdicts, severities, and attack examples for MEDIUM+.
5. **Verification** — independently re-trace every MEDIUM+ TRUE POSITIVE through the actual code (attack-example + precondition reachability + integration boundary). Drop/downgrade what does not hold.
6. **Output** — write the structured findings file per `references/findings-format.md`.

## Non-negotiables
- **Context isolation:** the validator never receives the finder's reasoning or exploration — only the final findings list. Passing the finder's scratch work to the validator defeats the purpose of the two-agent design.
- **Coverage gate:** every non-test backend file in the change must be explicitly accounted for before the critical pass. Silence is not coverage.
- **Attack-example gate:** no finding ships at MEDIUM+ without a concrete, code-traced attack example that proves the vulnerable state is reachable.
- **Read-only by default for PR mode:** when reviewing a GitHub PR, never post comments, reviews, approvals, labels, branches, or commits, and never trigger workflows. All findings go to the local findings file.

## Output
A structured markdown findings file. No HTML report and no chat widget — findings list only.

## Agents
- `security-paranoid-reviewer` — aggressive first-pass finder.
- `security-critical-reviewer` — skeptical validator.
Files in this package (4)
  • SKILL.md 3 KB
  • references/coverage-inventory.md 3 KB
  • references/findings-format.md 3 KB
  • references/pipeline.md 9 KB

Versions

The database has no other skills named teamsecure.

Database snapshot: 13.11.2026 · package version 13d31a2b494e (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100security-diff-scan
    Use when the user asks for a security review of a pull request, commit, branch diff, working-tree patch, or other Git-backed change set.
  • 100pr-quality-security
    Scan a local diff for vulnerabilities, secret exposure, and OWASP Top 10 anti-patterns, and return a PASS/WARN/CRITICAL_FAIL verdict. Use when you say `security review my changes`, `run the security gate`, or `check this diff for vulnerabilities`. Do NOT use to run all six axes…
  • 100security-review
    Security review via Codex exec. Use when: OWASP Top 10:2025 audit, dependency vulnerability check, security-sensitive changes. Not for: code review (use codex-code-review), test review (use test-review). Output: security findings + audit report.
  • 98security-review
    This skill should be triggered when a security code review, or security variation review is requested. You will be asked to review changes the agent or operator has made, a diff, a bug-id, or a Gerrit CL number.
  • 90commit-security-scan
    Scan code changes for security vulnerabilities using Bug Hunter-native artifacts and STRIDE context. Use whenever the user asks for PR security review, commit-diff scanning, staged-change security checks, branch-comparison security review, or pre-merge security analysis of changed code.
  • 100pr-quality-security
    Scan a local diff for vulnerabilities, secret exposure, and OWASP Top 10 anti-patterns, and return a PASS/WARN/CRITICAL_FAIL verdict. Use when you say `security review my changes`, `run the security gate`, or `check this diff for vulnerabilities`. Do NOT use to run all six axes…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.