skills/bulls-cows/skills/yy-mode-plan/Gen Agent Trust Hub

yy-mode-plan

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it processes untrusted user instructions to generate implementation plans.
  • Ingestion points: User-provided task descriptions or commands (e.g., /yy-mode-plan followed by a request) which are used to populate plan files.
  • Boundary markers: Absent; the skill does not provide instructions to the agent to distinguish between its own logic and potentially malicious instructions embedded within the user's task description.
  • Capability inventory: File system write operations (creating plan markdown files in detected or specified directories) and the NotifyUser notification tool.
  • Sanitization: Absent; the skill does not specify validation, escaping, or filtering of user input before it is written into the plan document.
  • [SAFE]: The skill's primary function acts as a defensive security control by strictly prohibiting any edits or non-read-only tool usage until the user has reviewed and explicitly confirmed a generated plan.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 06:35 AM