seo-meta-optimizer
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill analyzes untrusted external data (user content and keywords) to generate metadata and code components. It lacks explicit delimiters or instructions to ignore commands that might be embedded in the input text.
- Ingestion point: Content and keyword analysis instructions in
SKILL.md. - Boundary markers: Absent.
- Capability inventory: Generates text metadata and static site components (code snippets) in
SKILL.md; references reading additional local files (implementation-playbook.md). - Sanitization: Absent.
Audit Metadata