market-brand
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and analyzes content from user-provided URLs, which serves as an ingestion point for untrusted data that could contain malicious instructions.
- Ingestion points: Target URLs including homepages, about pages, and social media profiles analyzed in references/brand-workflow.md.
- Boundary markers: The instructions in SKILL.md do not define specific delimiters or boundary markers to isolate untrusted web content from the agent's internal logic.
- Capability inventory: The skill uses browser tools or analyze_page.py to read content (references/brand-workflow.md) and writes the resulting brand guidelines to the local file BRAND-VOICE.md (SKILL.md).
- Sanitization: There is no evidence of content sanitization or validation for the data retrieved from external sources across any of the referenced files.
Audit Metadata