market-audit
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content fetched from user-provided URLs, creating an attack surface for indirect prompt injection.
- Ingestion points: The
WebFetchtool is used to retrieve content from a homepage and five interior pages of a target website (Phase 1,SKILL.md). - Boundary markers: The instructions do not define clear delimiters or use "ignore instructions" wrappers for the content fetched from the external URL.
- Capability inventory: The skill has the capability to read local files (
COMPETITOR-REPORT.md,BRAND-VOICE.md), write a consolidated report to the filesystem (MARKETING-AUDIT.md), and output summaries to the user's terminal. - Sanitization: There is no evidence of sanitization, filtering, or validation performed on the external content before it is passed to the five specialist subagents for analysis.
Audit Metadata