taste-review
Fail
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The bash script programmatically accesses the macOS Keychain using the
security find-generic-passwordcommand to retrieve a secret OAuth token.- [COMMAND_EXECUTION]: The skill directs the agent to execute multiple shell commands, including system utilities for credential retrieval and theclaudeCLI for external processing.- [PROMPT_INJECTION]: The instructions explicitly guide the agent to 'Run outside the sandbox when required' and request 'reusable approval,' which are clear attempts to override the default security boundaries and sandbox constraints of the execution environment.
Recommendations
- AI detected serious security threats
Audit Metadata