wordpress-writer-social

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches an official brand writing style guide from the WordPress organization's GitHub repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (post titles, URLs, and HTML) to generate social media copy.
  • Ingestion points: Data enters the agent's context through input fields described in the 'Source content' section.
  • Boundary markers: No explicit delimiters or isolation instructions are defined to separate the untrusted data from the system instructions.
  • Capability inventory: The skill is used exclusively for text generation and does not define tools for command execution, sensitive file access, or network requests to non-whitelisted domains.
  • Sanitization: The skill parses HTML for specific shortlink tags but does not perform general sanitization or filtering of the input content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 06:42 PM