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, the readContent function reads data from external files or stdin.
  • 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
Risk Level
SAFE
Analyzed
Oct 6, 2026, 11:52 PM