plan-with-me
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill directs the agent to inspect the local development environment, including architecture documentation, monorepo configurations, and project root files, to establish context before planning.
- [COMMAND_EXECUTION]: To ensure plan feasibility, the agent is instructed to execute shell commands to verify environment capabilities, such as database support or endpoint availability.
- [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by ingesting data from the local codebase and user-provided examples. Ingestion points: Local codebase files, monorepo configurations, and user-provided artifacts (Phase 0 and Phase 2). Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted data from agent instructions. Capability inventory: The agent can execute arbitrary shell commands for feasibility testing and write markdown files to the local file system. Sanitization: The instructions do not specify sanitization or validation logic for data retrieved from the codebase or user.
Audit Metadata