compare
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple local Python scripts (e.g.,
dfs_client.py,seo_lint.py,citation_score.py,report_publish.py) to gather data and generate reports. These scripts are invoked via the shell with arguments derived from user input (domains and keywords). - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes data from external sources (SEO data via DataForSEO and website content via on-page linting).
- Ingestion points: Data returned from
dfs_client.py,seo_lint.py, andcitation_score.pybased on target URLs. - Boundary markers: None explicitly defined in the prompt instructions to separate untrusted data from processing logic.
- Capability inventory: The skill can write files to the local file system (reports) and execute shell commands to run scripts.
- Sanitization: There are no explicit instructions to sanitize the content retrieved from external sites before including it in the generated report or using it for analysis.
Audit Metadata