prompt-protection

MITLicense declared in the package manifest.

Agent security runtime for Node.js and browsers: provenance-tracked tool-call guard (CaMeL-style), spotlighting, fuzzy canaries, and hybrid rules + embedded ML detection for prompt injection. Zero dependencies, TypeScript-first, published benchmarks.

prompt-injectionagent-securitytool-call-guardtaint-trackingspotlightingcanary-tokencamelmcp-security
100

Security score

0 known advisories in v3.1.1

0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.advisory penalty −0 · staleness penalty −0

Weekly downloads

Downloads across all versions in the last 7 days, from the official npm downloads API (api.npmjs.org).

—

Unpacked size

Size of v3.1.1 on disk after npm install extracts the tarball, as reported by the npm registry.

8.7 MB

Dependencies

Direct runtime dependencies declared by v3.1.1. Transitive dependencies are not counted here — use the lockfile audit for the full tree.

0

Last publish

When v3.1.1 was published to the registry. Long gaps can indicate an unmaintained package.

5 days ago

Security advisories

Vulnerabilities affecting v3.1.1 specifically, from OSV.dev — the open database aggregating the GitHub Advisory Database (GHSA) and CVEs. Links open the full advisory.

No known vulnerabilities affect v3.1.1.