seo-sxo
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes untrusted data from external sources.
- Ingestion points: The skill fetches and parses user-provided target URLs (via
render_page.pyandparse_html.py) and extracts data from Google Search results, including snippets, People Also Ask (PAA) questions, and ad copy. - Boundary markers: There are no explicit instructions or delimiters defined to isolate the retrieved content from the agent's instructions, nor are there warnings to ignore embedded commands in the external data.
- Capability inventory: The skill leverages capabilities to perform web searches, call external analysis scripts, and integrate with the DataForSEO API.
- Sanitization: No sanitization or filtering logic is mentioned to clean retrieved HTML or search data before the agent processes it.
- [COMMAND_EXECUTION]: The skill executes local scripts (
render_page.py,parse_html.py) located within the plugin's root directory to process target URLs. While this is a standard operational pattern for this type of agent skill, it involves passing user-supplied URLs to shell-executed Python scripts.
Audit Metadata