meta-tags-optimizer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a static template and instructional guide for SEO tasks. It does not utilize shell commands, file system writes, or network requests to unknown domains. All generated assets are restricted to standard HTML meta tags and CTR optimization recommendations.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied URLs and page content to generate meta tags, presenting an indirect prompt injection surface.\n
- Ingestion points: Untrusted data enters the agent context through the main prompt via
[content/URL]placeholders inSKILL.md.\n - Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the ingested content.\n
- Capability inventory: The skill's capabilities are limited to string generation and reading SEO metrics from integrated tools; it lacks high-privilege capabilities such as arbitrary command execution or external data exfiltration.\n
- Sanitization: There is no evidence of filtering or escaping logic applied to the input content before processing.\nGiven the restricted output format (HTML tags) and the absence of dangerous system tools, the risk from indirect injection is negligible.
Audit Metadata