pm-advisor-torres

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were detected. The skill's instructions are focused on providing educational and coaching advice using a specific framework.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface via the WebSearch tool used in the 'Torres 式研究' (Torres-style research) workflow step to gather external information about product outcomes and evidence. While this allows external data to enter the agent's context, it is constrained by a structured analysis workflow based on predefined mental models, which serves the skill's primary functional purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 02:39 AM
Security Audit — agent-trust-hub — pm-advisor-torres