skills/thoreinstein/agents/ultrathink/Gen Agent Trust Hub

ultrathink

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted external input and has the capability to write to the file system.
  • Ingestion points: The skill accepts arbitrary user-provided input and problem descriptions for analysis (SKILL.md).
  • Boundary markers: Absent; there are no explicit delimiters or instructions provided to the agent to disregard instructions potentially embedded within the problem descriptions.
  • Capability inventory: The skill is granted permissions for 'Read', 'Glob', 'Grep', and 'Write' tools (SKILL.md).
  • Sanitization: Absent; the instructions do not include any logic for validating or sanitizing the input before it is processed by the reasoning logic or used in tool calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 04:27 PM