platform-models-api-configure

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses bash to execute a bundled script (scripts/get-orgjwt.sh) and standard CLI tools (curl, jq, sf). The script is used to perform a standard OAuth 2.0 client_credentials flow to obtain an access token from the user's own Salesforce instance.
  • [EXTERNAL_DOWNLOADS]: The skill uses curl to interact with the Salesforce Models API (api.salesforce.com) and the user's Salesforce instance URL for authentication. These are trusted destinations within the context of the skill's purpose for a Salesforce-authored skill.
  • [CREDENTIALS_UNSAFE]: The skill instructs users to store sensitive credentials (SF_CLIENT_ID, SF_CLIENT_SECRET) in a local file (.orgjwt.env). However, it follows security best practices by explicitly instructing the user to set permissions to chmod 600 and add the file to .gitignore to prevent accidental exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 04:34 PM
Security Audit — agent-trust-hub — platform-models-api-configure