threat-actor-profiling
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather data from external, untrusted intelligence sources such as OSINT tools (VirusTotal, Shodan), community sharing platforms, and vendor reports to build profiles. Malicious actors could potentially embed instructions in these external reports to influence the agent's analysis or report generation.
- Ingestion points: External intelligence gathering described in Step 2 (External intelligence section).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the gathered data.
- Capability inventory: The skill uses reporting and visualization tools (
visualize:show_widget) to present the final analysis. - Sanitization: No explicit sanitization or validation steps for external content are provided in the workflow.
Audit Metadata