seo-competitor-pages
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8). It is designed to ingest and process content from external competitor URLs provided by the user to generate comparisons, alternatives, and feature matrices. This creates a vector where malicious instructions embedded in competitor websites (e.g., in HTML comments or hidden text) could potentially influence the agent's output.
- Ingestion points: The
argument-hintandError Handlingsection indicate the skill accepts and attempts to access external URLs ([url or generate] [competitor]). - Boundary markers: The skill lacks explicit instructions to the agent to ignore embedded instructions within the fetched web content.
- Capability inventory: The skill primarily generates markdown and JSON-LD content; it does not show evidence of dangerous subprocess calls or file system writes.
- Sanitization: There is no mention of sanitizing or filtering the content retrieved from external URLs before processing it.
Audit Metadata