bd-source-adapter

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill outlines a workflow for ingesting data from WordPress data stores (comments, posts, metadata) into the agent's context via hydration into DataObjects. \n
  • Ingestion points: Data is read from WordPress database functions such as get_comment_meta and get_post_meta within adapters in the src/Source/ directory. \n
  • Boundary markers: The instructions do not specify the use of delimiters or specific instructions to ignore embedded content when processing this external data. \n
  • Capability inventory: The skill describes capabilities for running development tools including phpunit, phpstan, and WP-CLI commands. \n
  • Sanitization: The workflow does not explicitly describe sanitization or validation of the content retrieved from the database before it is used by the agent.\n- [EXTERNAL_DOWNLOADS]: The skill refers to an external GitHub repository (github.com/lonsdale201/better-data) for documentation. This resource is owned by the skill author and represents legitimate project documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:06 PM
Security Audit — agent-trust-hub — bd-source-adapter