File appears to expose a hardcoded API secret or token.
Critical
- Code
- suspicious.exposed_secret_literal
- Location
- test/picoclaw_security_guardian_sandbox_regression.sh:88
Security audit
picoclaw-security-guardian
Security checks across malware telemetry and agentic risk
Overview
This appears to be a disclosed Picoclaw security-checking skill whose local file reads and report writes match its stated purpose.
Install this for Picoclaw security review workflows, not general OpenClaw hook execution. Keep advisory feeds in verified mode, use unsigned modes only for short documented emergencies, and run profile generation against the intended PICOCLAW_HOME because it will read local Picoclaw configuration and write a profile report there.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
63/63 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.exposed_secret_literal