seo-content-gap
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its processing of external SEO data. It retrieves competitive keywords, page titles, and URLs from the DataForSEO API and instructs the agent to analyze this content to generate a content roadmap. Malicious instructions embedded in competitor metadata could potentially influence the agent's behavior.
- Ingestion points: Competitive SEO metrics and metadata retrieved from the
domain_overview.pytool in theSKILL.mdfile. - Boundary markers: Absent; there are no clear delimiters or instructions telling the agent to treat the tool's output as untrusted data.
- Capability inventory: The skill utilizes the
Bashtool for script execution and theWritetool for file modifications (e.g., writing the.envfile). - Sanitization: Absent; the skill does not specify any sanitization, validation, or escaping of the data fetched from the external API.
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute local utility scripts for credential management (preflight.sh), verification (keyword_research.py), and SEO data processing (domain_overview.py).
Audit Metadata