seo-ecommerce
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill functionality is driven by the execution of several local Python scripts, including
scripts/fetch_page.py,scripts/parse_html.py, andscripts/dataforseo_merchant.py. These scripts handle network requests to fetch product pages and interact with the DataForSEO Merchant API. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests and processes data from external websites.
- Ingestion points: External HTML content is fetched from user-provided URLs via
scripts/fetch_page.pyand processed inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore or isolate potential instructions embedded within the fetched HTML.
- Capability inventory: The skill can execute local subprocesses (Python scripts) and perform file writes to the
.seo-cache/directory. - Sanitization: There are no explicit sanitization or filtering steps mentioned for the fetched HTML before it is parsed and analyzed by the agent.
Audit Metadata