project-research-v3
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documentation and configuration do not contain any malicious patterns, obfuscation, or unauthorized data access commands.- [COMMAND_EXECUTION]: The skill instructs the agent to verify project information by analyzing code, configurations, and runtime command outputs, which is consistent with its stated purpose of project research.- [EXTERNAL_DOWNLOADS]: Information gathering is performed through well-known services (Google, Playwright), with instructions prioritizing official documentation and first-hand sources over untrusted summaries.- [PROMPT_INJECTION]: Robust guardrails are included to mitigate indirect prompt injection. The agent is specifically instructed to distinguish third-party statements from verified facts and to treat external data as discovery material rather than definitive evidence.
Audit Metadata