ai-seo
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to perform an 'AI Visibility Audit' which involves checking brand presence across various AI platforms. This ingestion of external, untrusted data creates a surface for indirect prompt injection.\n
- Ingestion points: Data retrieved from external AI search platforms (ChatGPT, Perplexity, Google) and competitor websites during the visibility audit phase (
SKILL.md).\n - Boundary markers: The instructions do not include guidance for the agent to use delimiters or ignore embedded instructions when reading external content.\n
- Capability inventory: The skill assumes the agent has access to web search or browsing tools to gather the audit data.\n
- Sanitization: No sanitization or validation of the content fetched from external sources is specified.\n- [NO_CODE]: The skill consists entirely of Markdown-based documentation and reference materials. No executable scripts (Python, JavaScript, Shell) or configuration files that trigger code execution were identified.
Audit Metadata