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-skills --skill exempt-vulngit clone --depth 1 https://github.com/harness/harness-skillsWrote 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-skills/exempt-vuln)<a href="https://agentmods.dev/skills/harness/harness-skills/exempt-vuln"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/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-skills/exempt-vuln"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/exempt-vuln.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 245 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 315 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- exempt-vuln — 100% identical, 0 lines differ
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.
- 12d ago First seen · 518 lines · 184 tokens per session scan A 51b5f8df9b3d
exempt-vuln is a skill published in the GitHub repository harness/harness-skills (106 stars, last pushed 3d 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.