inboundfy-seo
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from URLs and local project files to generate SEO reports, which is a potential surface for indirect prompt injection.
- Ingestion points: The skill accepts a URL or local file path as input and reads business context from
.inboundfy/directories. - Boundary markers: No explicit instruction delimiters or 'ignore embedded instructions' warnings are present in the provided files, though they may exist in the referenced shared configuration files (
../_shared/). - Capability inventory: The skill reads files, likely fetches web content from provided URLs, and writes/updates SEO reports in the local filesystem.
- Sanitization: No explicit sanitization or validation of the ingested external content was identified in the prompt instructions.
Audit Metadata