interview
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface detected.
- Ingestion points: The skill reads a file if the provided topic ($0) is a file path.
- Boundary markers: None. The skill does not use delimiters or instructions to ignore embedded commands within the read file.
- Capability inventory: The skill uses
AskUserQuestionto interact with the user and is instructed to read files from the filesystem. - Sanitization: No sanitization or validation of the file content is performed before processing.
Audit Metadata