asb-interview-goals
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input during the Phase A intake and writes it into a GOALS.md file, creating a potential surface for indirect prompt injection where malicious instructions in the user data could influence downstream tools. Ingestion points: User responses regarding business stage and decisions. Boundary markers: Absent; instructions do not require the use of delimiters or ignore-instructions warnings for external content. Capability inventory: The agent possesses the capability to write and update the GOALS.md file. Sanitization: No validation or escaping of user input is specified.
- [SAFE]: The skill includes a link to the author's official documentation at asmartbear.com, which is a legitimate vendor resource used for educational purposes.
Audit Metadata