blog-taxonomy

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to synchronize taxonomy data with various CMS platforms including WordPress, Shopify, Ghost, Strapi, and Sanity. These operations use the user-provided CMS_URL and are essential for the skill's primary functionality.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and parses blog content to generate tag suggestions. 1. Ingestion points: Reads local files or remote data during the Tag Suggestion Workflow. 2. Boundary markers: No specific delimiters are defined to isolate untrusted content from the agent's instructions. 3. Capability inventory: Ability to make network requests (POST/GET) and perform file reads. 4. Sanitization: No content sanitization or instruction-filtering is mentioned in the analysis process.
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by advising users to store credentials in environment variables rather than hardcoding them in files or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 08:44 AM
Security Audit — agent-trust-hub — blog-taxonomy