alchemy-and-hermetic-traditions-expert
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's research workflow presents a surface for indirect prompt injection.
- Ingestion points: In
modules/research-checklist.md, the agent is instructed to perform web searches and capture up-to-date sources from external websites. - Boundary markers: There are no instructions to use delimiters or ignore instructions within the retrieved web content, which could lead the agent to follow malicious prompts embedded in external data.
- Capability inventory: The workflow suggests using tools to distill information from sources like Wikipedia or Arxiv into the agent's context.
- Sanitization: No validation or sanitization steps are defined for the content fetched from the web before it is integrated into the skill's modules.
Audit Metadata