backlink-audit
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data sources, specifically backlink exports in CSV format from tools such as Google Search Console, Ahrefs, or Semrush.\n
- Ingestion points: Processes user-supplied CSV attachments containing backlink data (SKILL.md).\n
- Boundary markers: The instructions lack explicit delimiters or warnings for the agent to disregard instructions that might be embedded within the CSV data (e.g., in anchor text or URL fields).\n
- Capability inventory: The skill performs complex linguistic analysis on anchor text and referring domain profiles, which requires processing attacker-controlled strings.\n
- Sanitization: There is no evidence of sanitization or validation logic to filter out potential injection strings from the external data exports.
Audit Metadata