skills/picgo/skills/picgo-upload/Gen Agent Trust Hub

picgo-upload

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to interact with the PicGo ecosystem, including node scripts/gui-upload.mjs for the desktop application, picgo upload for the CLI, and npm install picgo -g for setup. These commands are the primary method of providing the skill's functionality.
  • [EXTERNAL_DOWNLOADS]: The skill guides the user to install the picgo package from the official NPM registry if it is missing. This refers to a well-known service and is a standard requirement for the tool's operation.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles user-provided files (images, PDFs, Zips) which could theoretically contain malicious instructions designed to influence the agent during metadata extraction or description generation. The skill mitigates this by providing clear operational boundaries and requiring user confirmation for sensitive content.
  • [PRIVILEGE_ESCALATION]: While the skill mentions sudo npm install as a solution for permission errors, it explicitly commands the agent NOT to run this automatically. It instead requires the agent to present the command for the user to execute manually, ensuring the user maintains control over elevated permissions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 02:14 AM