gsc-seo-optimizer
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external search data from Google Search Console (via CSV/ZIP imports and API calls), which represents a surface for indirect prompt injection. If an attacker could control search query data or page content indexed by Google, they might attempt to influence the agent's analysis.\n
- Ingestion points:
scripts/import_gsc.py(CSV/ZIP imports) andscripts/gsc_fetch.py(API data).\n - Boundary markers: Instructions mandate that the agent must confirm the exact property, search type, and date range with the user before interpreting data to ensure the scope is correct.\n
- Capability inventory: The agent is authorized to analyze search data and, with explicit user approval, propose or execute content edits within the project's CMS or repository.\n
- Sanitization: Content is parsed using standard Python library tools for CSV and JSON format verification.\n- [COMMAND_EXECUTION]: The provided test suite uses command execution to verify the functionality of the skill's internal scripts.\n
- Evidence:
tests/test_gsc.pyusessubprocess.runto executescripts/import_gsc.pyas a CLI tool during unit testing. This is a standard development practice for integration testing and is limited to the skill's own distributed code.
Audit Metadata