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

plan-with-me

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run local shell commands to verify technical feasibility, such as testing database extensions or API endpoint formats during the planning phase.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting workspace files and user examples without explicit sanitization or boundary markers.
  • Ingestion points: Project-specific files (e.g., .cursor/, .agents/, CONTRIBUTING.md, ARCHITECTURE.md) and user-provided data samples or screenshots in Phase 0 and Phase 2.
  • Boundary markers: Absent; the instructions do not define specific delimiters or instructions to ignore embedded commands within ingested content.
  • Capability inventory: The agent is authorized to read and write files within the workspace and execute shell commands to verify technical assumptions.
  • Sanitization: None; the skill does not describe any mechanism for filtering, escaping, or validating the content of external data sources before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 03:38 PM
Security Audit — agent-trust-hub — plan-with-me