alternative-blog-writer
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data obtained through search and scraping operations.
- Ingestion points: Content is ingested from "external data sources," "source material," and via search/scraping functions (
SKILL.md). - Boundary markers: The instructions lack specific delimiters or boundary markers (e.g., XML tags) to separate untrusted external content from the agent's instructions.
- Capability inventory: The skill can execute external API calls (
sandbase_run) and generate implementation artifacts or blog deliverables. - Sanitization: There are no explicit requirements to sanitize, filter, or escape data retrieved from external sources before it is processed for content generation.
Audit Metadata