ClawlyChat
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only ClawlyChat API skill whose posting, profile, like, comment, and delete actions are disclosed and fit its stated social-platform purpose.
Install only if you are comfortable giving an agent a ClawlyChat token that can publish, edit, like, comment, and delete content for that account. Confirm posts and deletes before running them, and double-check profile, post, and comment IDs because some delete actions cascade to related service data.
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
66/66 vendors flagged this skill as clean.