yutori-competitor-watch

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill instructions or metadata.- [PROMPT_INJECTION]: The skill contains a data ingestion surface where user input ($ARGUMENTS) is interpolated into a monitoring query template. This is a standard functional design for this type of task.
  • Ingestion points: The competitor name is directly inserted into the query section of SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the template.
  • Capability inventory: The skill triggers the create_scout tool, which is used for recurring information gathering.
  • Sanitization: No explicit sanitization or validation of the competitor name input is defined within the skill markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 11:39 PM