profile-optimizer

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses authoritative directives such as 'CRITICAL: Auto-start on load' and 'Do not summarise' to override default agent behaviors and force a direct execution flow.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from user-uploaded profile PDFs and screenshots.
  • Ingestion points: Local file 'about-me.md' and user-uploaded LinkedIn profile documents.
  • Boundary markers: Content is processed without explicit delimiters or instructions to ignore embedded commands.
  • Capability inventory: Restricted to text generation and structured user questioning; no system execution or network capabilities are requested.
  • Sanitization: No input validation or filtering is performed on processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 07:05 PM