image-seo-audit
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and analyze content from external URLs, specifically parsing HTML tags and attributes like alt text. This introduces a surface for indirect prompt injection, as malicious instructions could be embedded in the audited website's code to attempt to influence the agent's behavior during the analysis.
- Ingestion points: The URL argument and the external HTML content (img, picture, source tags) fetched by tech-seo-auditor.py.
- Boundary markers: None identified; the skill directly processes attributes as text for quality assessment.
- Capability inventory: The skill uses a script (tech-seo-auditor.py) to fetch pages and reads brand profiles for context; it does not demonstrate data exfiltration or system-level write capabilities.
- Sanitization: No specific sanitization, filtering, or escaping mechanisms for external content are described in the instructions.
Audit Metadata