apple-logarchive
Pass
Audited by Gen Agent Trust Hub on May 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill leverages native macOS utilities including /usr/bin/log, ls, wc, head, and tail to facilitate log investigation. It also incorporates a Python command for JSON data processing in complex workflows.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes system logs, which can contain untrusted strings from various applications. 1. Ingestion points: System logs retrieved via the
/usr/bin/log showcommand. 2. Boundary markers: No explicit markers or instructions are provided to help the agent distinguish log content from task instructions. 3. Capability inventory: The agent is granted read access to the filesystem and text processing tools via Bash. 4. Sanitization: There is no specified logic for sanitizing or escaping the content of the log messages before they are processed by the agent.
Audit Metadata