contentstudio

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to install the contentstudio-cli global package from the official NPM registry. This is a standard dependency for the skill's functionality and originates from the trusted vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-generated content from social media platforms through the social inbox and comment management features.
  • Ingestion points: Data enters the agent's context through inbox:list, inbox:messages, and inbox:comments (found in src/commands/inbox.ts).
  • Boundary markers: While the skill does not use specific delimiters for displaying external content, the instructions explicitly mandate using --dry-run and obtaining user approval before any outgoing mutation.
  • Capability inventory: The skill has significant capabilities, including posting to social networks (posts:create), replying to customers (inbox:send), and managing workspace members (team:add).
  • Sanitization: Instructions emphasize manual verification of content before sending, providing a human-in-the-loop safety mechanism.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:16 AM
Security Audit — agent-trust-hub — contentstudio