user-research-synthesis

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted data sources like interview transcripts and survey results. Evidence: 1. Ingestion points: interview transcripts, survey results, and user feedback (SKILL.md frontmatter). 2. Boundary markers: Absent; no specific delimiters or instruction-ignore blocks are defined. 3. Capability inventory: None; the skill is purely instructional and performs formatting/reasoning without external side effects. 4. Sanitization: Absent; content is directly mapped to reporting templates.
  • [No Code] (SAFE): This skill contains no executable scripts, shell commands, or dependency requirements, significantly reducing the attack surface.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:09 AM