dino-dinox

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of the 'dino' CLI tool for managing local data, authentication via 'dino auth login', and updating the software using system package managers through 'dino update'.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process unstructured note and task content.\n
  • Ingestion points: Note and todo content retrieved via 'dino note search', 'dino note detail', and 'dino todo search' subcommands (SKILL.md).\n
  • Boundary markers: Absent; the documentation does not suggest the use of delimiters or 'ignore' instructions for the agent when reading knowledge base content.\n
  • Capability inventory: The agent can execute a wide range of CLI subcommands including writing to the database, modifying tags/boxes, and performing network synchronization.\n
  • Sanitization: Absent; there is no indication that markdown content is sanitized or validated for malicious instructions before being returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 08:53 PM