spend-audit

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the webshare CLI available via the official vendor repository on GitHub and a Homebrew tap. These are recognized as legitimate vendor resources for providing the necessary auditing functionality.
  • [COMMAND_EXECUTION]: The skill is configured to use a specific set of webshare CLI commands through the Bash tool. The allowed-tools list in the manifest is scoped to data retrieval operations (e.g., list, show, stats, account), aligning with the skill's stated read-only purpose and minimizing the attack surface.
  • [CREDENTIALS_UNSAFE]: The skill requires a WEBSHARE_API_KEY to be provided by the user via environment variables. It does not contain hardcoded secrets and follows standard security practices for managing credentials with command-line interfaces.
  • [DATA_EXFILTRATION]: Account information and usage data retrieved via the CLI are processed locally to generate markdown reports in the ./webshare-audits/ directory. No unauthorized network communication or external transmission of sensitive account data was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:48 PM
Security Audit — agent-trust-hub — spend-audit