@msm-core/safety
UNLICENSEDAgent trust guardrails — PII detection/redaction (Luhn-checked), REVERSIBLE redaction with a token map, prompt-injection detection, groundedness, and a tool-output safety filter. Pure, deterministic, dependency-free.
100
Security score
0 known advisories in v0.2.0
Weekly downloads
—
Unpacked size
38.5 kB
Dependencies
0
Last publish
8 days ago
Security advisories
No known vulnerabilities affect v0.2.0.