author-expertise
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized actions were detected. The skill's behavior is consistent with its stated purpose of SEO auditing.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it requires the agent to ingest and analyze external data.
- Ingestion points: The skill instructs the agent to verify rendered HTML and HTTP responses from audited websites.
- Boundary markers: No specific delimiters are defined to isolate external content from the agent's instructions.
- Capability inventory: The skill involves reviewing metadata, templates, and structured data using standard auditing capabilities.
- Sanitization: No explicit sanitization or filtering of the retrieved content is mentioned in the instructions.
Audit Metadata