rsdoctor-v2-upgrade
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands for dependency installation, production builds, and the
rsdoctor-agentCLI to verify the migration. These actions are performed within the user's project environment. \n- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading and acting upon external project files, which creates a potential for indirect instructions to influence the agent. \n - Ingestion points: The agent reads
package.json, lockfiles, build scripts, and Rsdoctor data files from the project. \n - Boundary markers: There are no defined boundary markers or instructions to ignore embedded commands within the analyzed project files. \n
- Capability inventory: The skill utilizes shell execution capabilities for build and validation steps. \n
- Sanitization: No specific sanitization or validation logic is mentioned for the content retrieved from project configuration files.
Audit Metadata