tutor-skills
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (PDFs, HTML, EPUB, and source code) to generate Obsidian StudyVaults and quiz content. This ingestion creates a potential vector for indirect prompt injection, where malicious instructions hidden in these files could attempt to manipulate the agent's behavior during the setup or tutoring phases.
- Ingestion points: The
tutor-setupskill scans, extracts, and validates content from various document formats and source code projects. - Boundary markers: The skill instructions do not specify the use of clear delimiters or instructions for the agent to ignore embedded commands within the processed materials.
- Capability inventory: The skill utilizes the
Read,Write, andBashtools, providing a range of capabilities that could be targeted if an injection is successful. - Sanitization: No specific content sanitization or validation logic is described for the data extracted from source materials.
- [EXTERNAL_DOWNLOADS]: The documentation provides a command to install the skill via
npx skills add RoundTable02/tutor-skills, which downloads and executes code from an external repository managed by the vendor.
Audit Metadata