seo-audit
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by analyzing homepage signals from websites to determine business types and drive audit logic. This constitutes a potential attack surface for indirect prompt injection if the scanned website contains malicious instructions designed to influence the agent.
- Ingestion points: Homepage signals and website content used for detection and auditing (SKILL.md).
- Boundary markers: None explicitly defined in the orchestrator instructions to delimit external content.
- Capability inventory: File system write operations for report generation at
.fuse-seo/reports/and invocation of multiple sub-agents (SKILL.md). - Sanitization: No explicit sanitization or filtering of external website content is described in this orchestrator's logic.
Audit Metadata