meta-tags-optimizer
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and reference material focus entirely on SEO optimization tasks, such as generating title tags, meta descriptions, and social media tags (Open Graph/Twitter Cards). The logic is purely instructional and template-based.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external web content and user-provided descriptions to perform its function. This creates an interface for indirect prompt injection if the ingested content contains adversarial instructions. However, the risk is classified as low/safe because the skill's output is restricted to generating text for meta tags and does not involve any privileged system operations.
- Ingestion points: User-provided URLs and content strings in
SKILL.md. - Boundary markers: Not present; the agent is instructed to analyze the content directly.
- Capability inventory: The skill is limited to text generation and does not utilize subprocesses, file system writes, or unauthorized network requests.
- Sanitization: Not explicitly implemented, though the highly specific task scope provides a natural constraint.
Audit Metadata