research
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected.
- [PROMPT_INJECTION] (SAFE): The skill contains no instructions attempting to override agent safety protocols or bypass system constraints.
- [EXTERNAL_DOWNLOADS] (SAFE): No third-party package installations or remote script downloads are defined in this file.
- [COMMAND_EXECUTION] (SAFE): While the skill references a slash command and external command documentation, it does not perform arbitrary shell command execution.
- [INDIRECT_PROMPT_INJECTION] (LOW): This skill is designed to ingest and synthesize data from external research agents (Perplexity, Claude, Gemini). This creates a known attack surface where malicious content within research results could potentially influence the agent's behavior.
- Ingestion points: External data processed via researcher agents and synthesized in the final report.
- Boundary markers: None explicitly defined in this markdown file; implementation details are likely in the referenced command file.
- Capability inventory: Agent orchestration and report synthesis.
- Sanitization: No explicit sanitization or filtering of research results is documented in the high-level skill definition.
Audit Metadata