analysis
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process external content which could contain malicious instructions meant to influence the analyst's tone or recommendations.
- Ingestion points: Untrusted data is ingested via the
{research_str}and news story parameters. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present to isolate user-provided data from system instructions.
- Capability inventory: The skill's capabilities are limited to generating natural language reports; it contains no subprocess calls, file-system operations, or network exfiltration logic.
- Sanitization: There is no evidence of input sanitization or validation of the provided strings.
Audit Metadata