explorbot-plan
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and executemdq-cliandexplorbot. These packages appear to be the official tools for the Explorbot platform and are used to validate and execute the generated test plans. - [COMMAND_EXECUTION]: The skill provides instructions to run shell commands via
npxfor markdown validation (mdq-cli) and test execution (explorbot). These commands are part of the intended workflow for managing test plans. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as feature descriptions, requirements, and documentation to generate structured markdown test plans.
- Ingestion points: Untrusted data enters the agent context through feature descriptions, user stories, or documentation provided by the user (SKILL.md).
- Boundary markers: The instructions do not specify boundary markers or delimiters to separate the user-provided documentation from the agent's instructions.
- Capability inventory: The skill invokes shell commands using
npxto validate markdown structure and run testing sessions. - Sanitization: No explicit sanitization, filtering, or escaping of the input documentation is mentioned before the agent processes it into the test plan format.
Audit Metadata