online-tutor
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions for content generation and tutoring. It does not utilize any scripts, commands, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external "source material," which is an inherent surface for indirect prompt injection. However, the risk is assessed as safe because the skill has no access to dangerous tools, network capabilities, or sensitive files.
- Ingestion points: The "full source" material provided to the agent as described in
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or boundary markers for the ingested source text.
- Capability inventory: The skill contains no tools or instructions for shell execution, network requests, or filesystem writes.
- Sanitization: No explicit sanitization or filtering of source content is described; the skill relies on the agent's internal safety filters and manual review steps.
Audit Metadata