planview
Fail
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (CRITICAL): The skill contains multiple instructions to execute remote scripts via
curl -fsSL https://plannotator.ai/install.sh | bashandirm https://plannotator.ai/install.ps1 | iexinSKILL.md. These patterns allow an attacker to execute arbitrary code on the host system without prior inspection. - [EXTERNAL_DOWNLOADS] (HIGH): The domain
plannotator.aiis not a trusted source. The skill installs binary tools and agent plugins from this unverified source, bypassing standard package registry security controls. - [COMMAND_EXECUTION] (MEDIUM): The skill encourages the modification of other agent environments (Claude Code and OpenCode) through plugin installations, which could serve as a vector for persistence or lateral movement within the user's development environment.
Recommendations
- HIGH: Downloads and executes remote code from: https://plannotator.ai/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata