AI agent supply-chain security
Every agent
obeys someone.
Inspect the instructions, skills, and tools your AI agents trust. Find prompt injection, hard-coded secrets, and unsafe commands before your agents run them.
- Read-only inspection
- Secrets redacted in reports
- No cloning or code execution
The platform in numbers
Inspection at a glance
- Files inspected
- - All-time activity, including repeat scans
- Unique skill snapshots
- - Registered HIGH/CRITICAL snapshots
- Unique security findings
- - Distinct findings, not repeat scan hits
Evidence of inspection, not a safety rating. Snapshots can be partial; content versions are not unique people, publishers or approved skills.
Registry breakdown & counting methodology
- Complete supported skill versions
- -
- MCP definition snapshots
- -
Scanner
Inspect before your agent obeys
Upload agent files, paste a skill, or point at a repository. Results appear in seconds.
Seen this skill before?
How it works
Three steps, zero trust
-
01
Collect
Upload files, paste skill content, or name a GitHub, GitLab or Azure DevOps repository. For repositories, AgentLens lists the commit's file tree and inspects only files an agent would load.
-
02
Inspect
An isolated scanner applies injection, credential, execution, and exfiltration rules. Nothing is run, rendered, or followed.
-
03
Report
Every signal is mapped to a file, line or decoded JSON pointer, severity, MITRE ATLAS technique, and research reference. Detected secret values are redacted before they reach your screen.
Explore
Explore AgentLens
Defensive inspection informed by SkillVenom red-team research and samples.
Fingerprint search
Look up a file or content fingerprint in the AgentLens registry.
Search the registry 02Coverage
The threat classes, agent ecosystems and file types AgentLens inspects, mapped to MITRE ATLAS.
See detection coverage 03Samples
A catalogue of defanged, test-backed attack use cases, every detection proven by a working sample.
Browse the catalogue 04Research
The incidents, papers and advisories behind every rule, searchable and linked to the source.
Read the research 05Newsletter
Read past editions of Agent Security Weekly.
Browse the archive