Prompt Guard
SuspiciousCK: Criticalby seojoonkim
11.6K downloads54 starsv3.6.217 versions
Description
650+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, cascad...
Changelog
No code or documentation changes detected in this release. - Version number updated from 3.6.0 to 3.6.2. - No functional or documentation changes present.
Published Jan 29, 2026Updated May 10, 2026
Security Analysis
ClawHub:
SuspiciousClawkeeper:
CK: CriticalRisk Score8.0 / 10
Critical risk — manual review strongly recommended. Score is the sum of weighted findings below.
Findings
43 files analyzedmedium|+2.0 pts
Contains executable handler files (js/ts/sh/py)
medium|+1.0 pts
Unusually large file: scripts/detect.py (101KB)
medium|+1.5 pts
Binary file detected: pyproject.toml (application/toml)
low|+0.5 pts
43 files (typical skill has 1-3)
critical|+3.0 pts
Flagged as suspicious by ClawHub
ClawHub scanned: May 10, 2026
Rescanned every 6 hours by Clawkeeper
Deploy Securely
Free to scan. Pro to deploy.