imessage

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the imsg CLI tool to perform operations such as listing chats, reading history, and sending text messages.
  • [PRIVILEGE_ESCALATION]: The skill instructions require the user to grant 'Full Disk Access' and 'Automation' permissions to the terminal application. This grants the agent broad access to the user's private message database and the ability to control other applications.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a third-party dependency from a personal Homebrew tap (steipete/tap/imsg). While the developer is known in the community, this is an external binary dependency.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface where malicious instructions could be ingested from incoming messages.
  • Ingestion points: External data is fetched via imsg history and monitored via imsg watch as described in SKILL.md.
  • Boundary markers: Absent; there are no instructions provided to the agent to treat message content as untrusted data or to use delimiters.
  • Capability inventory: The agent can send messages, list all chats, and access local files to send as attachments.
  • Sanitization: Absent; the skill does not describe any validation or filtering mechanisms for the message data it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 05:57 AM