SECOPS
Agentic security triage for labeled GitLab MRs with Linear follow-ups
An agent reads each security-labeled GitLab MR, judges its risk and which security domain owns it, assigns the right reviewer.
How it runs
The automated pipeline, trigger to output.
- TriggerGitLab MR receives security labelGitLab
- ActionAgent reads MR diff and descriptionOpenAI
- LogicClassify risk and owning domain
- ActionAssign reviewer and comment reasoning on MRGitLab
- OutputOpen Linear follow-up issue with rationaleLinear
What it does
For merge requests tagged with a security label, an agent reviews the diff and description, classifies the risk and the owning domain (appsec, infra, data, crypto), and assigns the appropriate reviewer. When the change needs work beyond the MR itself, it opens a Linear issue capturing the risk rationale and links it back to the MR.
When to use it
Use it when a flat label-to-reviewer mapping isn't enough and you want judgment on ambiguous changes plus durable follow-up tracking, without a human triaging every MR.
How it works
- 1A GitLab webhook fires when an MR receives a security label.
- 2The agent pulls the MR diff, title, and description as context.
- 3It reasons about risk level and which security domain should own the review.
- 4It assigns the chosen reviewer on the MR and posts its reasoning as a comment.
- 5When follow-up is needed, it creates a Linear issue with the risk summary and a link to the MR for tracking to closure.
Set it up
What you configure once, before turning it on.
- 1Connect GitLabRepos, MRs, pipelines, registry.
- 2Connect LinearIssues, projects, cycles, triage.
- 3Connect OpenAIModels, embeddings, files.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More SecOps workflows
Post-Revocation Verification and Audit Logging
After a key is revoked, it confirms the old credential actually fails, verifies the replacement works.
Page on-call when a WAF rule mass-blocks legitimate traffic
On demand or every few minutes, it detects a single Cloudflare WAF rule suddenly blocking a broad spread of ASNs and paths (a likely false-positive storm).
PII Content Scan on New Dropbox External Share
When a file gets an external Dropbox link, it reads the file content, uses an AI classifier to detect PII or secrets.
Compile a weekly WAF tuning review with trends to Confluence
Every week an agent rolls up Cloudflare WAF block clusters by rule and ASN, compares them to prior weeks for trend direction.
Sensitive Dropbox Link Owner Remediation Loop
When a newly created Dropbox shared link points to a sensitive file, this workflow DMs the file owner, gives them a deadline to justify or revoke it.
GitLab Push Secret Detection to Block and History Purge
On a GitLab push that contains a detected secret, it revokes the exposed credential, opens a tracking issue with git-history purge instructions.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.