stock-metrics
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill acts on untrusted external 'Website Data' which can contain malicious instructions intended to subvert the agent's behavior.
- Ingestion points: The
{extract_results}variable inSKILL.mdis used to inject raw website content directly into the prompt. - Boundary markers: Absent. The input is not wrapped in delimiters or accompanied by instructions to ignore embedded commands, increasing the risk of the agent obeying instructions found within the data.
- Capability inventory: No dangerous capabilities (file writes, subprocesses, network requests) are present in this skill.
- Sanitization: No sanitization or validation of the input data is performed before processing.
Audit Metadata