Open Source Malware (OSM)
Detect and verify malicious AI skills in your software supply chain
Open Source Malware (OSM) is a database and API service that identifies malicious AI skills used in agentic AI workflows. It allows platform engineers and developers to check whether a specific AI skill contains known indicators of compromise before integrating it into their toolchains. Users can query the API with a skill's identifier to receive a verdict on whether it has been flagged as malicious.
OSM provides a rate-limited API that accepts a skill's resource identifier and ecosystem, then returns whether the skill has been identified as malicious based on its database of verified malicious AI skills.
Platform engineers and developers integrating AI agent skills into their software supply chains
Background.
- Status
- launched
- Business model
- freemium
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.