skills/getsentry/dotagents/dex/Gen Agent Trust Hub

dex

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx @zeeg/dex to execute the task management tool if it is not already installed in the environment's PATH. This command fetches the package from the standard NPM registry.\n- [COMMAND_EXECUTION]: The skill functions by executing various dex CLI commands (e.g., create, list, complete, show) to manage task state and local files.\n- [PROMPT_INJECTION]: The skill ingests and displays task content (names, descriptions, and results) which may originate from untrusted sources or previous sessions (Indirect Prompt Injection).\n
  • Ingestion points: Task data is retrieved from local JSON files in the .dex/tasks/ directory through commands like dex show <id> --full and dex list (SKILL.md, cli-reference.md).\n
  • Boundary markers: The skill does not implement explicit delimiters or warnings to isolate ingested task content from instructions.\n
  • Capability inventory: The skill possesses capabilities for shell command execution and local file system access.\n
  • Sanitization: No specific sanitization or validation logic is observed for the content of tasks before they are presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 02:21 PM