ts-plan
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to verify that development tools are available in the environment (e.g., running tools with a no-op flag like
--help).- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests untrusted data from the repository, including source code, tests, and documentation, to inform its planning process. It lacks explicit instructions to sanitize or delimit this external content to prevent it from influencing the agent's instructions.
Audit Metadata