skills/dotlas/skills/plan-with-me/Gen Agent Trust Hub

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
Risk Level
SAFE
Analyzed
Jul 26, 2026, 01:43 PM
Security Audit — agent-trust-hub — plan-with-me