tutor-with-notes
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses content from local files (~/.tutor-notes/ or learning/ directory) to customize the tutoring session, creating an indirect prompt injection surface.
- Ingestion points: Reads previous session records from
NOTES.mdand misconception logs to determine which topics to skip or review. - Boundary markers: Absent; there are no instructions to the agent to treat the content of these files as untrusted or to use delimiters to prevent instruction injection.
- Capability inventory: The agent is granted permission to read and write markdown files and create directories on the local filesystem.
- Sanitization: Absent; the instructions do not require the agent to validate or sanitize the content of the notes before incorporating them into the reasoning process.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform extensive filesystem operations, including creating and managing the
~/.tutor-notes/directory and writing multiple markdown files. While these operations are necessary for the skill's primary function of tracking long-term mastery, they utilize the agent's command execution capabilities to modify the user's home environment.
Audit Metadata