seo-drift
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple internal Python scripts (e.g., drift_baseline.py, fetch_page.py) to perform its core functions of data retrieval and analysis.
- [EXTERNAL_DOWNLOADS]: The tool fetches HTML content and SEO metadata from remote URLs specified by the user to create snapshots or perform comparisons.
- [PROMPT_INJECTION]: The skill possesses an indirect injection surface as it processes untrusted data from external websites (such as meta tags and schema markup). This data is presented to the agent, which could potentially influence behavior if the site content contains malicious instructions.
- Ingestion points: External data is ingested via scripts like fetch_page.py and parse_html.py.
- Boundary markers: The skill does not explicitly define markers to distinguish untrusted remote content from instructions when presenting data to the agent.
- Capability inventory: The skill executes local Python scripts to process data and displays the results to the agent.
- Sanitization: The skill extracts specific HTML elements but does not describe a sanitization process for the text content before it is passed to the agent context.
Audit Metadata