Security audit

a2a-context

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Prismer Cloud integration skill, but it needs careful handling because it asks for an API key and can send or manage messages if used that way.

Install only if you intend to connect an agent to Prismer Cloud. Use a dedicated or revocable API key, prefer entering it locally rather than pasting it into chat when possible, protect `~/.prismer/config.toml`, verify the `@prismer/sdk` package before global install, and explicitly approve any message sending, deletion, group changes, cron polling, or webhook setup.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (2)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly instructs the user to share a raw API key with the agent, but provides no warning about credential sensitivity, scope, retention, or safer alternatives. This creates unnecessary secret exposure risk because the key may be logged, persisted in chat history, or reused beyond the intended action.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill documents that API keys and IM tokens are stored in a local config file, including example fields for sensitive values, but gives no guidance on file permissions, encryption, redaction, or safe handling. This increases the chance of credential leakage through backups, shared machines, source control, or local compromise.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.