create-research-brief

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is text-based prompt generation and research strategy design. It does not perform any direct command execution, network requests to untrusted domains, or file system modifications.
  • [DATA_EXFILTRATION]: While the skill facilitates the analysis of best practices (including topics like authentication and secrets management), it focuses on general industry patterns rather than accessing or exfiltrating user-specific sensitive data.
  • [PROMPT_INJECTION]: The skill includes logic to process structured inputs from upstream agents, which presents a surface for indirect prompt injection. However, since the skill's primary output is text-based research plans rather than executable code, the risk is minimal and does not escalate the safety verdict.
  • [EXTERNAL_DOWNLOADS]: All references to model profiles and prompt fragments are contained within the skill's own local file structure. No unverified external scripts or executable dependencies are downloaded during operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 09:08 AM
Security Audit — agent-trust-hub — create-research-brief