brand-positioning-audit
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data by fetching and analyzing content from user-provided brand URLs, creating an attack surface for indirect prompt injection.
- Ingestion points: The
Phase 2: Analysis — Research + Scoringsection inSKILL.mdinstructs the agent to fetch a brand's website and capture verbatim copy, including headlines, about page language, and differentiation claims. - Boundary markers: The instructions lack explicit boundary markers (like XML tags or delimiters) or specific warnings to ignore instructions embedded within the fetched content.
- Capability inventory: The agent uses the extracted content to calculate scores across six dimensions and generate a 'Rewrite Pack' containing headline and CTA options. While no critical system commands are triggered by this data, it can bias or override the agent's audit results.
- Sanitization: There is no mention of sanitizing, escaping, or validating the external content before it is interpolated into the analysis phase.
Audit Metadata