start

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): No malicious instructions, safety bypasses, or persona-breaking commands were detected. The prompt strictly defines a Senior Product Analyst persona.
  • [Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local file paths and contains no network-related commands (curl, wget, etc.).
  • [Indirect Prompt Injection] (SAFE): The skill processes user-provided ideas to generate a structured PRD. 1. Ingestion points: User dialogue responses. 2. Boundary markers: Absent in the markdown output template. 3. Capability inventory: None (the skill provides no tools for file-system writing; it instructs the agent to generate text). 4. Sanitization: None. This is categorized as safe because it is the primary purpose of the prompt and involves no automated execution of the generated content.
  • [No Code] (SAFE): This skill consists entirely of markdown-based system instructions and does not include any scripts, binaries, or configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 12:44 AM