Concurrent Process Algebra for AI Agents

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent agent-orchestration helper, but users should audit the external npm dependency before installing it.

Install this only where agent-driven code and branch changes are acceptable. Review or pin the `cpa-agents` npm package before use, run it first in a development workspace, and use explicit user approval for branch creation, file writes, merges, rollback, and model fan-out tasks.

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

Findings (1)

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The skill explicitly documents workflows that create branches, write code, and revert code, but it does not warn users that these operations can modify repository state or files. In an agent skill context, that omission is risky because users may invoke examples like saga-based execution assuming analysis-only behavior, leading to unintended side effects, destructive rollback, or changes to active worktrees.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal