quiz-me
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local file system at a specific hardcoded path:
/Users/james/Vaults/zettelkasten/. - Reads configuration from
Home 🏡.mdand content from theProcessed/directory. - Creates and modifies files in the
.quiz/hidden directory, specifically.quiz/progress.mdand.quiz/cards/. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from the user's vault notes.
- Ingestion points: Arbitrary text is read from markdown files in the
Processed/folder and existing card banks during session initialization and card generation. - Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore instructions embedded within the processed vault notes.
- Capability inventory: The skill has permissions to read local files and write/append to specific files in the vault. It does not have network access or arbitrary command execution capabilities.
- Sanitization: There is no evidence of sanitization, filtering, or validation for content ingested from the vault files.
Audit Metadata