seo-technical
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface where malicious instructions embedded in a processed website could influence the agent's behavior. • Ingestion points: The skill is intended to analyze external URLs and fetch data such as robots.txt and HTML content as described in SKILL.md. • Boundary markers: There are no explicit delimiters or instructions in SKILL.md to treat the ingested external content as untrusted or to isolate it from the agent's system instructions. • Capability inventory: SKILL.md specifies the use of DataForSEO MCP tools (e.g., on_page_instant_pages, on_page_lighthouse) which provide the capability to read content from the live web. • Sanitization: No sanitization, validation, or filtering mechanisms for the external data are described in the skill.
Audit Metadata