interview
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill provides a surface where untrusted data could influence agent behavior.
- Ingestion points: User input enters the skill through the
$ARGUMENTSvariable in theSKILL.mdfile and through responses to theAskUserQuestiontool. - Boundary markers: The skill does not use explicit delimiters (e.g., XML tags, triple backticks) or specific 'ignore embedded instructions' warnings to isolate user-provided content from the system instructions.
- Capability inventory: The skill has the ability to write files to the local system (
Writetool) and interact with the user (AskUserQuestiontool). - Sanitization: No evidence of input validation, escaping, or filtering of the external topic or user responses was found.
Audit Metadata