This product was not featured by Product Hunt yet.
It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).

Product upvotes vs the next 3

Waiting for data. Loading

Product comments vs the next 3

Waiting for data. Loading

Product upvote speed vs the next 3

Waiting for data. Loading

Product upvotes and comments

Waiting for data. Loading

Product vs the next 3

Loading

Assay

Execution-grounded security verifier for AI agent skills

Assay runs an AI agent skill in a sandbox on macOS or Linux against a real agent, captures what it actually did, and checks it against what it claims to do. Signed evidence, honest verdicts, and an audit gate. Open source, v0.1.3.

Top comment

Hi Product Hunt — I'm Ali, the maker. I built Assay because "is this AI agent skill safe?" is usually answered by a static scan or a model's opinion. Assay runs the skill in a sandbox on macOS or Linux against a real agent, captures what it actually did, and checks that against what the skill declares. The verdict is backed by a signed record a third party can verify offline. v0.1.3 is open source on PyPI. It covers Claude Code/OpenClaw skills and Cursor rules; MCP has an inspector and a conservative report. It does not claim a skill is safe: CLEAN means the run matched the declared scope, and UNVERIFIED is never a pass. macOS and Linux today; Windows via WSL2. Linux network access uses Landlock/seccomp and needs Linux 6.7+ and libseccomp. No web app. MCP runs on macOS and Linux. I'd especially value feedback on the verdict model and the audit workflow. Ask me anything.

About Assay on Product Hunt

“Execution-grounded security verifier for AI agent skills”

Assay was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #450 on the daily leaderboard. Assay runs an AI agent skill in a sandbox on macOS or Linux against a real agent, captures what it actually did, and checks it against what it claims to do. Signed evidence, honest verdicts, and an audit gate. Open source, v0.1.3.

On the analytics side, Assay competes within Developer Tools, Artificial Intelligence, GitHub and Security — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Assay performed against the three products that launched closest to it on the same day.

Who hunted Assay?

Assay was hunted by Ali Haqiqi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.

For a complete overview of Assay including community comment highlights and product details, visit the product overview.