seo
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data and web content, which are untrusted inputs.
- Ingestion points: Web content and external data processed via BrowserOS (SKILL.md).
- Boundary markers: The skill lacks explicit technical delimiters but instructs the agent to treat external data as hostile.
- Capability inventory: The skill utilizes the ExecutionProxy Interface for terminal actions and MemoryStore Interface for persistent markdown artifacts (SKILL.md).
- Sanitization: Instructions require the agent to redact secrets and PII before sharing context with subagents.
Audit Metadata