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 $ARGUMENTS in SKILL.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, and Write tools 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
Risk Level
SAFE
Analyzed
Mar 18, 2026, 08:09 AM