Skip to content

Add agentcheck to Guardrails & Compliance - #86

Open
uchit wants to merge 1 commit into
ProjectRecon:mainfrom
uchit:add-agentcheck
Open

Add agentcheck to Guardrails & Compliance#86
uchit wants to merge 1 commit into
ProjectRecon:mainfrom
uchit:add-agentcheck

Conversation

@uchit

@uchit uchit commented Aug 2, 2026

Copy link
Copy Markdown

Adds agentcheck, a zero-dependency CLI that produces an audit evidence pack for an agent deployment.

A note on placement. This section is described as middleware to enforce business logic and safety policies on inputs and outputs, and agentcheck is not middleware — it is an assessment tool that runs against a deployment rather than sitting in the request path. I put it here because "Compliance" is in the section title and nothing else fit better, but if you would rather it went elsewhere, or warranted a separate Assessment & Evidence section, I am happy either way. Say the word and I will move it.

What it does differently. It refuses to produce a score. Most controls for agentic systems can only be attested by a person, and a tool that quietly converts an attestation into a measurement launders an opinion into evidence. So it reports two counts and never sums them:

  • DECLARED — a human asserted it, with a name attached
  • VERIFIED — a read-only command ran, with its output in the report

A command that runs and fails counts as neither. There is a test asserting the output object exposes no aggregate score field, so the one design promise cannot regress quietly.

Why it works as a CI gate. It exits non-zero only when a pack is indefensible — a control claimed met with no evidence recorded, or claimed met while one of its prerequisites is not met (tool authorisation cannot be met if the agent has no identity of its own to authorise). An honest unknown passes, because unknown is the correct starting state and a tool that punishes it teaches people to guess.

Against the contribution criteria

  • Directly related to agent security: covers OWASP LLM01 (indirect prompt injection through retrieval and tool-result paths) and LLM06 (excessive agency — tool authorisation outside the model, bounded blast radius, action reversibility)
  • Open source: MIT. Control set published separately under CC BY 4.0
  • Maintained: first release today; CI green on Node 18/20/22/24, 19 tests, zero dependencies
  • Not a duplicate: checked, no existing entry

Disclosure: I am the author.

npm: https://www.npmjs.com/package/@uchit/agentcheck
Docs: https://hellouchit.com/agents/

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant