Repository · npm

GitHub Actions/prompt-protection

Provenance-tracked tool-call guard for JS agents (CaMeL-style), fail-closed, zero dependencies. Taints tool results, trusts what the user named, and blocks untrusted data reaching network, email, exec, file or payment sinks. Text detection, spotlighting a

View on npmReport an issue

Owner	GitHub Actions
License (as declared)	MIT
Stars	0
Forks	0
Main language	javascript
Created	20 October 2026
Last updated at source	20 October 2026

npmjavascriptagent-securitytool-call-guardtaint-trackingcamelfail-closedmcp-securityai-agentsowasp-agenticprompt-injectionspotlightingcanary-tokenaudit-logopentelemetryagent-threat-rulesatrllm-securityjailbreakai-safetyprompt-sanitizationopenaianthropiclangchain

Embed this entry

<iframe src="https://silytics.si/embed/item/675425ac-16be-4d78-8004-9ad30da54af9" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Stars, last 7 days

3,496 now (-239 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.

More from GitHub Actions

aiRepository
am-i-vibingRepository
chatRepository
langchainRepository
assistant-streamRepository
tokenxRepository

Silytics shows public metadata from npm and links to the original. Information may be incomplete or out of date. Last refreshed 21 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.