agent-research
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns, instructions, or obfuscated content were detected in the skill definitions.
- [PROMPT_INJECTION]: The skill ingests untrusted research topics through the argument-hint parameter, creating an indirect prompt injection surface. 1. Ingestion points: Research questions provided in the input topic. 2. Boundary markers: No explicit boundary markers or instruction-ignoring warnings are defined in SKILL.md. 3. Capability inventory: Use of Bash, Write, Edit, and Grep tools. 4. Sanitization: No specific input validation or escaping mechanisms are documented.
- [COMMAND_EXECUTION]: The skill includes the Bash tool in its allowed tools list to facilitate research operations.
Audit Metadata