seo-article-writer
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes content from external, untrusted websites (top SERP results) which presents an attack surface for indirect prompt injection.
- Ingestion points: Step 3 of the process in
SKILL.mdusesWebFetchto read content from URLs provided by the user or identified in search results. - Boundary markers: Absent. There are no instructions to the agent to treat the fetched content strictly as data or to ignore any potential instructions embedded within the external pages.
- Capability inventory: The skill has permission to read internal business knowledge files (
knowledge/brand/voice.md,knowledge/services/, etc.) and write to the local file system (output/seo-article/). - Sanitization: The skill does not define any sanitization, filtering, or validation steps for the content retrieved from external sources before it is processed.
- [EXTERNAL_DOWNLOADS]: The skill utilizes a
WebFetchtool to retrieve data from remote websites. While intended for competitive analysis, this facilitates network requests to arbitrary external domains.
Audit Metadata