create-interview-guide
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the files it reads for context. \n
- Ingestion points: Reads files from
.chalk/docs/product/(e.g., product profiles, research syntheses) and user-provided$ARGUMENTSinSKILL.md. \n - Boundary markers: The instructions do not define any delimiters or instructions to ignore embedded commands within the processed files. \n
- Capability inventory: The skill uses
Read,Glob,Grep, andWritetools to interact with the local filesystem. \n - Sanitization: There is no evidence of validation or sanitization of the content read from external files or user arguments before it is processed or used to construct file paths.
Audit Metadata