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.
- Author
- mattermost ↗
- Repository
- mattermost-ai-marketplace ↗
- Licence
- MIT
- Last repository change
- 26.10.2026
Assessment and security
- Files in this package
- 4
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.
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
- When to use
- Input modes
- Pipeline (overview — full detail in references/pipeline.md)
- Non-negotiables
- Output
- Agents
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…