pre-publish-post-assistant
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection. The skill processes untrusted content from local files and URLs which could contain malicious instructions.
- Ingestion points: User-provided file paths (e.g., /path/to/draft.md) and URLs.
- Boundary markers: Absent. The skill does not define delimiters or specific instructions to ignore embedded commands within the draft data.
- Capability inventory: The skill is configured to read local files and perform network requests to a WordPress GraphQL endpoint.
- Sanitization: No explicit sanitization or validation of the processed draft content is mentioned in the instructions.
Audit Metadata