wordpress-publisher
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content (from files or standard input) that is then processed by the agent to be formatted and published. This provides a surface for attackers to embed malicious instructions within the content being published.
- Ingestion points: In
scripts/wp-publish.js, thereadContentfunction reads data from external files orstdin. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided when the agent is asked to process or wrap the content in RTL tags.
- Capability inventory: The skill possesses network writing capabilities, enabling it to perform HTTP POST requests to an external WordPress API and upload files to the media library.
- Sanitization: The skill does not perform sanitization, escaping, or schema validation on the ingested content before it is sent to the WordPress REST API.
Audit Metadata