Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add harness/harness-ai --skill exempt-vulngit clone --depth 1 https://github.com/harness/harness-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/harness/harness-ai/exempt-vuln)<a href="https://agentmods.dev/skills/harness/harness-ai/exempt-vuln"><img src="https://agentmods.dev/badge/skills/harness/harness-ai/exempt-vuln/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/harness/harness-ai/exempt-vuln"><img src="https://agentmods.dev/badge/skills/harness/harness-ai/exempt-vuln.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00184 | $0.06799 |
| Opus 5 | $0.00092 | $0.03400 |
| Sonnet 5 | $0.00037 | $0.01360 |
| Haiku 4.5 | $0.00018 | $0.00680 |
Grade A, and why
exempt-vuln scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to exempt-vuln — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exempt Vulnerability
Create a security exemption (waiver) for one or more Harness STO vulnerabilities. STO has two places a user can request an exemption from, and each one allows a different set of scopes:
| Where the user is in the Harness UI | Scopes they can request |
|---|---|
| Vulnerabilities tab of a specific pipeline execution | This Project, This Pipeline, This Target |
| All Issues page (the project-wide baseline) | This Project only |
The reason for the difference is simple: rows on the All Issues page are aggregated across
executions and don't carry an execution_id, so the backend has no pipeline or target context
to attach a narrower scope to. Org- and Account-scoped exemptions are not created here at all;
they're produced later by approving an existing exemption at a higher scope (via
harness_execute resource_type=security_exemption action=approve body={scope:'ORG'|'ACCOUNT'}),
which is outside the scope of this skill.
Instructions
Step 1 — Find out where the user is starting from
Ask the user, in plain language:
Which view are you in?
- The Vulnerabilities tab for a specific pipeline execution, or
- The All Issues page (the project-wide baseline view).
If you have the URL handy, just paste it — I'll pull out the org, project, and execution from it automatically.
You also need:
- The org and project, unless they're already in session defaults or you can read them from a pasted URL.
- For the Vulnerabilities tab path: the execution ID, or any Harness URL that contains one.
A pasted Harness UI URL is always the fastest route. The MCP url parameter auto-extracts every
identifier in the path, so the user does not have to type anything else. The shapes to recognise:
| URL the user pastes | What it tells you | Which path |
|---|---|---|
…/sto/executions/{executionId}/pipeline |
The Vulnerabilities tab of one execution | Vulnerabilities path — extracts org_id, project_id, execution_id |
…/pipeline/orgs/{org}/projects/{project}/pipelines/{pipelineId}/executions/{executionId}/… |
A pipeline execution detail page | Vulnerabilities path — also extracts pipeline_id |
…/sto/issues or …/sto/issues/{issueId} |
The All Issues page | All Issues path — extracts org_id, project_id only |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 518 lines · 184 tokens per session scan A 51b5f8df9b3d
exempt-vuln is a skill published in the GitHub repository harness/harness-ai (19 stars, last pushed 18d ago), licensed Apache-2.0. It adds 184 tokens to every session and 6,799 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to exempt-vuln, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…