ai-seo
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions, reference guides, and templates for marketing professionals. There are no suspicious code patterns, obfuscated commands, or unauthorized data access attempts.
- [METADATA_POISONING]: There is a discrepancy between the platform-identified author ('iwanhe') and the author named in the skill's frontmatter ('Alireza Rezvani'). This is likely a placeholder or copy-paste error and does not impact the safety of the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from an external file ('marketing-context.md') to inform its strategy. While this constitutes an untrusted data ingestion surface, the skill does not possess any tools or capabilities (such as shell access, network operations, or file-writing tools) that could be exploited via prompt injection. Evidence: Ingestion points: marketing-context.md (SKILL.md); Boundary markers: Absent; Capability inventory: None (no shell, network, or write-access tools defined); Sanitization: Absent.
Audit Metadata