gsc
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted search console data such as queries and URLs which could contain malicious instructions designed to influence the agent.
- Ingestion points: Data enters the context via Google Search Console API responses processed in scripts/gsc_query.py during analytics and inspection commands.
- Boundary markers: The SKILL.md file contains explicit warnings for the agent to treat query text, page URLs, and inspection results as untrusted data and never as instructions.
- Capability inventory: The skill has capabilities to perform network requests to Google API endpoints and read/write local configuration files with strict permissions (mode 0600).
- Sanitization: The scripts perform structural and type validation but do not filter the semantic content of search queries for prompt injection attacks.
Audit Metadata