scimax
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled local Org-mode files which may contain malicious instructions designed to subvert the agent's behavior. \n
- Ingestion points: User notes (.org files) and journal entries are processed via the Read tool, Grep tool, and 'scimax search' command output. \n
- Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to disregard instructions found within the data being processed. \n
- Capability inventory: The agent has permissions to execute any 'scimax' CLI command and has unrestricted file Write access to the filesystem. \n
- Sanitization: No sanitization, escaping, or validation of the contents of the Org-mode files is performed before they are ingested into the agent's context.
Audit Metadata