axiom-xclog-ref

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for executing the local binary ${CLAUDE_PLUGIN_ROOT}/bin/xclog to manage and monitor iOS simulator processes and system logs.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by processing untrusted application logs. Ingestion points: Console output and system logs are retrieved via the launch, attach, and show commands in SKILL.md. Boundary markers: Although the tool provides structured JSON output, the skill lacks instructions for the agent to treat log content as untrusted or to ignore embedded instructions. Capability inventory: The agent can write log data to the local filesystem and execute subsequent commands. Sanitization: No filtering or sanitization of the captured logs is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 08:47 PM