skills/arcblock/idd/intent-interview/Gen Agent Trust Hub

intent-interview

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION] (SAFE): The skill contains purely instructional content for structuring an interview process. No malicious bypass patterns or hidden instructions were found.
  • [DATA_EXPOSURE] (SAFE): No sensitive data paths, hardcoded credentials, or exfiltration patterns are present in the provided markdown.
  • [REMOTE_CODE_EXECUTION] (SAFE): No external dependencies, scripts, or download commands are included or referenced.
  • [COMMAND_EXECUTION] (SAFE): No shell commands or system-level operations are present.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes untrusted user input (product ideas) which is then used to generate specifications. While this defines an ingestion surface for potential indirect injection, the skill itself provides no executable capabilities or scripts that could be exploited by such an injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:11 PM