tutor
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to perform web research to gather information for tutoring. This involves processing external content which may contain untrusted data.
- Ingestion points: The "Quick research" step in
SKILL.mdutilizesweb searchorWebFetchto gather topic information. - Boundary markers: The instructions do not define specific delimiters or warnings to isolate external research data from the agent's core instructions.
- Capability inventory: The skill is designed for instructional dialogue and utilizes search capabilities; it does not request dangerous file-system access or arbitrary command execution.
- Sanitization: No explicit instructions for sanitizing or filtering the content retrieved from the web are provided.
- [EXTERNAL_DOWNLOADS]: The
README.mdfile provides links to the author's GitHub repository (github.com/synapseradio/ai-skills) for installation and to download the packaged skill file. These are legitimate resources provided by the skill author for distribution and setup.
Audit Metadata