seo-optimize
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes content from external URLs provided by the user.
- Ingestion points: Data enters the agent's context through the 'on_page_content_parsing' tool, which fetches and parses content from a user-specified URL.
- Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard embedded instructions within the parsed external content.
- Capability inventory: The skill possesses the capability to read local project files (e.g., keyword-data.md, outline.md) and execute multiple DataForSEO API tools for content and search analysis.
- Sanitization: There is no evidence of sanitization or validation of the external content before it is used for comparison against local files or reported to the user.
- [DATA_EXFILTRATION]: The skill demonstrates a pattern of accessing local file data and interacting with external services.
- It reads files within the 'docs/seo/' directory to retrieve keywords and outlines. While these are not sensitive system configuration files, the skill's workflow involves taking data from the local environment and potentially passing derived values to DataForSEO's external tools for analysis.
Audit Metadata