deep-research
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'exec' tool to run the 'deeptutor' binary for topic analysis. This is a vendor-owned resource (HKUDS) and is core to the skill's functionality.
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes data from external, untrusted sources.
- Ingestion points: The skill retrieves and processes information from 'web' and 'papers' sources via the deeptutor command (SKILL.md).
- Boundary markers: There are no instructions for the agent to use delimiters or ignore instructions that may be embedded within the research results.
- Capability inventory: The agent has access to the 'exec' tool to run shell commands.
- Sanitization: No explicit sanitization or filtering of external content is described before the data is integrated into the agent's context.
Audit Metadata