msal2020/skillguard
Audit agent skills & MCP servers for prompt injection, secret exfiltration, and tool poisoning
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| path | Path to scan, relative to the repository. | no | . |
| command | What to scan: ci | scan | mcp | skill | tools. | no | ci |
| min-severity | Only report findings at this severity or above (critical|high|medium|low|info). | no | high |
| fail-on | Fail the job on this verdict or worse: fail | warn | never. | no | fail |
Outputs
no outputs