wordpress-plugin-development
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes code snippets for AI integration that are vulnerable to indirect prompt injection (Category 8). * Ingestion points: Untrusted data enters the agent context through the $post->post_content variable in the my_plugin_generate_ai_summary function and the $input['content'] field in the my_plugin_generate_summary_cb function (file: SKILL.md). * Boundary markers: None. The snippets do not use delimiters or instructions to ignore embedded commands within the ingested content. * Capability inventory: The skill demonstrates the ability to write to the database via update_post_meta and return data through REST API endpoints. * Sanitization: While basic length limiting (substr) and tag stripping (strip_tags) are present, no sanitization or escaping is performed to prevent the ingested data from influencing the AI logic or bypassing instructions.
Audit Metadata