technology-radar
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a purely instructional framework for an AI agent to perform technology research and assessment. It does not define any programmatic actions, scripts, or system-level commands.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external information regarding technologies and frameworks, which constitutes a theoretical injection surface. However, the risk is mitigated by the lack of exploitable capabilities.
- Ingestion points: Untrusted data enters the context via the 'Inputs' section (technology names, project requirements, constraints) in SKILL.md.
- Boundary markers: No explicit delimiters or 'ignore' instructions are defined for the input data.
- Capability inventory: The skill possesses no dangerous capabilities; there are no file-write operations, network requests, or subprocess executions across the analyzed content.
- Sanitization: The skill includes an 'Input Sanitization' section explicitly stating that inputs are treated as read-only analysis targets and are not used in commands or file paths.
Audit Metadata