shareful-create

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill directs the agent to execute 'npx shareful-ai', which downloads and runs code from the npm registry. The package 'shareful-ai' is not from a trusted organization or repository.
  • [COMMAND_EXECUTION] (MEDIUM): The workflow involves interpolating user-supplied strings (title, tags, problem) into shell commands (e.g., 'npx shareful-ai create --title "..."'). This pattern is vulnerable to command injection if the agent does not strictly sanitize shell metacharacters provided by the user.
  • [REMOTE_CODE_EXECUTION] (MEDIUM): Use of 'npx' for a non-whitelisted package facilitates remote code execution of unverified scripts.
  • [DATA_EXFILTRATION] (LOW): The skill reads from '~/.shareful/config.json'. While this is the tool's own configuration, accessing files within hidden home directories is considered sensitive path access.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:26 PM