seo-aeo-geo
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to audit websites and analyze AI search engine outputs. This ingestion of untrusted external data creates an attack surface for indirect prompt injection, where a malicious third-party site could attempt to influence the agent's behavior.
- Ingestion points: The workflow requires the agent to "inspect rendered HTML and structured data" and "Query each of the major AI products" to analyze citations and search results (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters, XML tags, or system-level instructions to treat the analyzed content as data only or to ignore embedded instructions.
- Capability inventory: The agent is authorized to parse HTML, identify priority queries, perform web searches, and write a remediation strategy file (
aeo-geo-strategy.md) to the local filesystem (SKILL.md). - Sanitization: The skill does not include steps for sanitizing, escaping, or filtering content retrieved from target websites or external search engines before processing.
- [NO_CODE]: The skill consists entirely of markdown documentation and instructional frameworks. It does not include any scripts, executable binaries, or configuration files for automated processing.
Audit Metadata