canai-eeat
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local drafts, WordPress pages, and external URLs. Since it also has the ability to write or edit content, it is susceptible to indirect prompt injection if the audited content contains malicious instructions.
- Ingestion points: The skill reads content using Read, Grep, Glob, and wpcanai-read-meta tools from local files and WordPress environments.
- Boundary markers: No explicit boundary markers or delimiters are instructed for the untrusted input content to distinguish it from the agent's system instructions.
- Capability inventory: The skill utilizes Write and Edit tools, along with wpcanai-write-meta, wpcanai-write-post, and wpcanai-write-page for remediation.
- Sanitization: There is no mention of sanitizing or validating the input data before processing.
Audit Metadata