imessage
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to install the
imsgCLI from an external third-party Homebrew tap (steipete/tap/imsg). This introduces a dependency on code hosted and maintained outside of the primary platform. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted incoming data from iMessages which could contain malicious instructions.
- Ingestion points: Message content retrieved via
imsg historyandimsg listcommands inSKILL.md. - Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands within the message text.
- Capability inventory: The skill has access to
Bash,Read, andWritetools as defined in the frontmatter ofSKILL.md. - Sanitization: Absent; the skill does not specify any filtering or sanitization of message content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill relies on executing shell commands to interact with the local macOS Messages database. While these commands are specific to the
imsgutility, the use of theBashtool provides the underlying capability for local command execution.
Audit Metadata