tech-assessment
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied descriptions and requirements for technology evaluations. There is an inherent risk that these inputs could contain malicious instructions designed to influence the agent's assessment or behavior, as the instructions do not specify explicit boundary markers or sanitization steps for external data.
- Ingestion points: User prompts requesting assessments for specific technologies (e.g., 'assess Apache Kafka for our use case').
- Boundary markers: Absent; there are no instructions to ignore or treat embedded content in user input as untrusted.
- Capability inventory: The skill uses standard agent capabilities for reasoning and report generation; no high-risk tools are explicitly invoked in the provided files.
- Sanitization: Absent; the instructions do not require filtering or escaping user-provided technology data.
Audit Metadata