Verified policy definition
HIPAA PHI Baseline
Supported identifier, secret and injection checks with PHI-focused scoring weights.
Technical coverage, not certification
Pack names identify control intent. Detection and enforcement are limited to the configured validators and supported execution boundary.
- Version
- 1.0.0
- Category
- Data boundaries
- Evaluation Available
- true
- Domains
- HIPAA_PHI
- PCI
- SECURITY
- Controls
- Email, phone, SSN, MRN-like and card-number patterns
- Six normalized instruction-override phrase heuristics
- Structured credential fields and known secret patterns
- Thresholds
- warn: 1redact: 4block: 8escalate: 16
- Behavior
- The exact assigned ID and version select scoring weights, thresholds and enabled validators.
- BLOCKED and ESCALATE_HITL withhold protected output. Required transformations are applied and revalidated at supported boundaries.
- HIPAA_PHI findings have domain weight 3; SECURITY findings have weight 2. A supported email finding can escalate under this configuration.
- Limitations
- Pattern matching can produce false positives and miss sensitive data; it does not establish legal data classification.
- Pack names do not establish HIPAA, PCI DSS, accessibility or other regulatory compliance.
- A finding is not a completed remediation. Inspect the final enforcement outcome and returned artifact.
- Regulatory Pulse source coverage and draft state mappings do not establish installed jurisdiction-specific executable packs.
- Does not validate clinical correctness, lawful disclosure, a HIPAA security program or a business associate agreement.
Enabled validators
- pii-phi · 1.1.1
- prompt-injection · 1.2.0
- security-secrets · 1.1.0
Bounded examples
Request examples describe an exercise; they are not recorded execution evidence.
Fixed input hold scenario
{"scenarioId":"hitl-input"}The Developer Evaluation default fixture expects ESCALATE_HITL / HELD before the synthetic provider is invoked. A hold does not create an approval or automatic resume.
