elliot-sones/AgentGate Security & Trust Scan

Run AgentGate security and/or trust scans on an AI agent as part of your CI/CD pipeline. Fails the step when findings exceed the configured threshold.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
scan-typeWhich scan to run. One of: "trust", "security", or "both". Use "trust" to run static + runtime trust checks, "security" for red-team probing, or "both" to run the full combined scan. notrust
source-dirPath to the agent source directory (relative to the repo root). Used for static trust checks and manifest discovery. no.
manifestPath to the trust manifest file (relative to the repo root). Defaults to <source-dir>/trust_manifest.yaml. notrust_manifest.yaml
fail-onTrust verdict threshold that causes the step to exit with a non-zero code. One of: "allow_with_warnings", "manual_review", or "block". nomanual_review
agent-urlURL of a live hosted agent for runtime checks or security scanning. Required when scan-type is "security". Optional for trust scans. no""
output-dirDirectory where scan reports are written.noagentgate-reports
agentgate-versionVersion of agentgate to install. Defaults to the latest release. no""
anthropic-api-keyAnthropic API key used by AgentGate for LLM-based analysis and adaptive attacks. Pass this via a repository secret. no""
namedescription
verdictTrust verdict string from the scan (e.g. "allow", "allow_with_warnings", "manual_review", "block"). For security scans this is the pass rate.
findings-countNumber of findings returned by the scan.
report-pathPath to the primary JSON report file.