seo-article-finalizer
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted article content and SEO packets, creating a potential surface for instructions embedded in the data to influence agent behavior.
- Ingestion points: Reads proofed articles and 'SEO_PACKET ▸ Brief' documents in SKILL.md (Step 1).
- Boundary markers: Absent; the instructions do not provide delimiters or specific commands to ignore potential instructions within the ingested article text.
- Capability inventory: The skill utilizes the
import_to_google_docfunction to create new files in Google Drive. - Sanitization: No explicit content sanitization or validation logic is mentioned for the article text before it is written to the output document.
- [EXTERNAL_DOWNLOADS]: The skill documentation provides an installation command that fetches components from a remote GitHub repository belonging to the author.
- Evidence:
npx skills add https://github.com/peter-tu-zynkr/zynkr-skill-builder --skill seo-article-finalizerin SKILL.md.
Audit Metadata