content-portability
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for importing content from local directories into a live WordPress site, creating a surface where malicious instructions in the imported files could influence agent behavior.
- Ingestion points: The skill reads from
manifest.json,content.json, andcontent.mdfiles within user-specified local directories (e.g.,./respira-export/). - Boundary markers: Absent. There are no instructions for the agent to use delimiters or ignore potential commands embedded within the text or metadata of the imported content.
- Capability inventory: The skill utilizes powerful write operations on the target WordPress site, including
wordpress_update_page,wordpress_update_post, andwordpress_inject_builder_content. - Sanitization: The instructions do not provide methods for sanitizing the imported HTML or Markdown content to prevent prompt injection payloads from being processed or stored on the target site.
Audit Metadata