← Index

io.github.sparkvibe-io/GuardianShield

io.github.sparkvibe-io/GuardianShield·v1.2.1·Security

AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
GUARDIANSHIELD_PROFILE

Default safety profile (general, education, healthcare, finance, children)

GUARDIANSHIELD_AUDIT_PATH

Path to the SQLite audit database

GUARDIANSHIELD_DEBUG

Set to 1 for debug logging

MCP quality score · maturity, not trust · methodology
freshness
19
completeness
10
installability
25
documentation
15
stability
10
Alternatives in Security