salaye
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to explain a supplied subject, which may involve processing untrusted or external data. It specifically implements boundary markers (triple backticks) to separate subject content from system instructions, which is a defensive measure. However, as the skill inherently acts on external inputs to form mental models, there is a low-level surface for indirect prompt injection if malicious instructions are embedded within the supplied subject text.
Audit Metadata