AI-Powered Meta Description Writer

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's installation instructions refer to downloading the package from the vendor's repository (agentskillexchange/skills) and the clawhub registry.
  • [COMMAND_EXECUTION]: The documentation provides shell commands using 'npx' and 'clawhub' to install the skill, which executes external binaries to fetch and configure the agent's environment.
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to the way it handles external data.
  • Ingestion points: The skill fetches existing page content through the WordPress REST API to use as context for generating descriptions.
  • Boundary markers: There are no defined delimiters or instructions to ignore embedded commands within the fetched WordPress content.
  • Capability inventory: The skill has the capability to write data to Yoast SEO REST API fields and perform batch operations on website pages.
  • Sanitization: There is no evidence of sanitization or validation of the fetched page content before it is interpolated into the prompt for the OpenAI API.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 05:47 PM