ai-overviews-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local scripts
scripts/dfs_client.pyandscripts/report_publish.pyto interact with the DataForSEO API and generate client-ready reports. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external content by fetching target URLs via
webfetchto perform structural audits. This introduces a risk where malicious instructions embedded in the analyzed pages could influence agent behavior. - Ingestion points: External URLs or page content processed as described in
SKILL.md. - Boundary markers: No clear delimiters or specific instructions are provided to the agent to ignore potentially malicious embedded content within the analyzed pages.
- Capability inventory: The skill has the ability to execute shell commands via local Python scripts and write results to the filesystem.
- Sanitization: There is no evidence of content sanitization or validation before the fetched data is processed by the agent.
- [DYNAMIC_EXECUTION]: The skill uses the
SEO_REPORTS_DIRenvironment variable to dynamically construct file paths for saving reports, which is a standard configuration pattern but relies on environment-specific variables.
Audit Metadata