consensus-tech-research

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is technical research and documentation. It explicitly states that it does not generate production code, scaffolding, or modify dependencies.
  • [DATA_EXPOSURE]: The skill writes output to a specific documentation directory (docs/research/), which is consistent with its stated purpose of generating technical selection reports.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection as it processes external data via search tools (anysearch) and local project records. However, the risk is minimal because the skill's capabilities are restricted to writing markdown reports and it lacks dangerous tools for execution or data exfiltration.
  • Ingestion points: Reads local CONTEXT.md, Architecture Decision Records (ADRs), and external web content via anysearch.
  • Boundary markers: No specific delimiters or "ignore" instructions are defined for the ingested data.
  • Capability inventory: File system write access limited to creating markdown reports in docs/research/. No subprocess execution, network exfiltration, or dynamic code evaluation.
  • Sanitization: No explicit sanitization or validation of external content is specified before interpolation into the research report.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 03:05 AM
Security Audit — agent-trust-hub — consensus-tech-research