gsc-assistant

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • No Code (SAFE): The skill consists entirely of natural language instructions and markdown templates. It does not include any Python scripts, Node.js code, or shell commands that could be used for malicious execution.
  • Indirect Prompt Injection (SAFE): The skill is designed to ingest data from external files (gsc-export.csv, sitemap.xml). While this constitutes an attack surface, the risk is negligible because the skill's logic is restricted to formatting data into markdown tables.
  • Ingestion points: Local gsc-export.csv and sitemap.xml files.
  • Boundary markers: None explicitly defined, relying on the agent's default processing of structured data.
  • Capability inventory: The skill only performs text transformation and file updates; no network or system-level capabilities are invoked.
  • Sanitization: No specific sanitization logic is provided, which is acceptable given the low-privilege markdown generation context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:55 PM