msal2020/skillguard

Audit agent skills & MCP servers for prompt injection, secret exfiltration, and tool poisoning

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
pathPath to scan, relative to the repository.no.
commandWhat to scan: ci | scan | mcp | skill | tools.noci
min-severityOnly report findings at this severity or above (critical|high|medium|low|info).nohigh
fail-onFail the job on this verdict or worse: fail | warn | never.nofail

no outputs