gsc-assistant

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources such as gsc-export.csv and sitemap.xml to populate tracking tables.
  • Ingestion points: gsc-export.csv and sitemap.xml files in the project directory.
  • Boundary markers: None explicitly defined to distinguish between data and instructions.
  • Capability inventory: Limited to local file writing and content organization within indexed.md and to-index.md.
  • Sanitization: Not specified; however, the skill's capabilities are restricted to formatting and categorizing URL data, posing minimal risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 10:13 PM
Security Audit — agent-trust-hub — gsc-assistant