seo-suite
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads from seo-project.yml and client profiles to load context such as audience, brand voice, and goals. 1. Ingestion points: seo-project.yml and client profiles loaded via python scripts/project_memory.py. 2. Boundary markers: Absent. There are no instructions to the agent to treat this data as untrusted or to ignore embedded instructions. 3. Capability inventory: The skill has the ability to execute multiple Python scripts (dfs_client.py, seo_config.py, report_publish.py) and write reports to the file system. 4. Sanitization: None mentioned for the data loaded from project memory.
- [COMMAND_EXECUTION]: The skill heavily relies on executing local Python scripts to interface with the DataForSEO API and generate client deliverables. Evidence: Invokes python scripts/dfs_client.py, python scripts/seo_config.py status, python scripts/project_memory.py, and python scripts/report_publish.py.
Audit Metadata