wordpress-plugin-development
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides template code for a WordPress AI Connector that processes content from posts or API inputs.
- Ingestion points: The
my_plugin_generate_summary_cbandmy_plugin_generate_ai_summaryfunctions inSKILL.mdingest raw post content and input data strings. - Boundary markers: The code snippets use simple string concatenation to build prompts (e.g.,
'Create a compelling 2-sentence summary... ' . $content) without using specific delimiters or instruction-isolation techniques. - Capability inventory: The plugin capabilities include network communication via
wp_ai_client_promptand database writes viaupdate_post_metaandregister_post_meta. - Sanitization: The code demonstrates the use of
sanitize_textarea_fieldon AI-generated output, but it lacks specific sanitization or filtering to prevent the input content from overriding the prompt's instructions.
Audit Metadata