Skills
skills/ninehills/skills/todo/Gen Agent Trust Hub

todo

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads task data from a workspace file that could be influenced by untrusted sources, creating a potential vector for indirect prompt injection.\n
  • Ingestion points: The skill ingests data from .alma/todos-<THREAD_ID>.md using the Read tool.\n
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the todo list content.\n
  • Capability inventory: The skill is authorized to use the Read and Write tools for file operations.\n
  • Sanitization: No sanitization, escaping, or validation is performed on the content read from the todo file.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:32 AM