c-contacts
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
osascriptutility to execute AppleScript for querying the macOS Contacts application. This is a standard automation method on macOS and is entirely consistent with the skill's stated purpose of managing contact information. - [PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by reading data from the macOS Contacts database, which could contain instructions intended to be interpreted by the AI agent.
- Ingestion points: Contact names, emails, and phone numbers retrieved from the Contacts application via AppleScript.
- Boundary markers: None are defined; data is retrieved and returned as raw strings.
- Capability inventory: The skill utilizes
osascriptfor local command execution. - Sanitization: No sanitization or validation of the data retrieved from the Contacts application is performed before it is added to the agent's context.
Audit Metadata