project-research

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill coordinates UX and technical research by reading local project metadata and using the web tools. It operates within the expected project directory structures and follows a logical workflow.
  • [COMMAND_EXECUTION]: Although "Bash" is listed in allowed-tools, no shell commands are invoked in the SKILL.md logic; the orchestration is handled by spawning a specialized researcher agent.
  • [EXTERNAL_DOWNLOADS]: "WebSearch" and "WebFetch" are utilized solely for data gathering as part of the primary research function. No remote code execution or suspicious external script downloads were identified.
  • [DATA_EXFILTRATION]: While the skill accesses project context (BRIEF.md, config.json), this information is used internally by the agent to inform its research and is not sent to unauthorized external endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 07:13 PM