marketing-ideas
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 retrieved through search, scraping, and enrichment tasks, creating a surface for indirect prompt injection if external content contains malicious instructions.
- Ingestion points: The skill ingests "source material" and performs "search, scraping, enrichment" using external data sources (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings for the agent when processing retrieved external content.
- Capability inventory: External data may influence parameters passed to vendor tools like
sandbase_run(references/sandbase-api-map.md). - Sanitization: There are no explicit instructions for the agent to sanitize or validate retrieved external data before it is incorporated into the prompt context.
Audit Metadata