smello-screenshot-maker

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local commands including node, npm, and python3. These are used to run screenshot generation scripts, install local dependencies, and process JSON data from a local API. This behavior is consistent with the skill's primary purpose of UI automation and documentation management.
  • [REMOTE_CODE_EXECUTION]: An automated scan flagged a curl | python3 pattern. However, the analysis shows the request targets localhost:5110 (the user's local Smello server) and the piped Python command is a static script provided in the documentation to filter JSON output, rather than executing arbitrary code from a remote source.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to run npm install within a local directory to prepare the environment. This is a standard procedure for JavaScript-based tools and relies on the user's local package.json configuration.
  • [DATA_EXFILTRATION]: Network activity is restricted to localhost domains (ports 5110 and 5111). These connections are used to fetch data from a local development server to populate the UI before capturing screenshots, representing internal communication rather than external data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 11:02 PM
Security Audit — agent-trust-hub — smello-screenshot-maker