tutor-me
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions in a markdown file and does not include any scripts, binaries, or other executable code.
- [SAFE]: Analysis of the instructions reveals no presence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms. The skill follows best practices for tutoring agents.
- [PROMPT_INJECTION]: The skill contains a potential surface for indirect prompt injection as it instructs the agent to consult external user-provided sources. This is classified as safe as it is central to the pedagogical purpose of the skill. * Ingestion points: Instructions in SKILL.md to check a "textbook, primary source, or reference" pointed to by the user. * Boundary markers: Not present. * Capability inventory: Implicit tool usage for searching or reading documents. * Sanitization: Not present.
Audit Metadata