deep-research
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use IPython for data calculations and the generation of charts and graphs. This execution is scoped to the skill's analytical requirements and represents standard functional behavior.
- [PROMPT_INJECTION]: The skill has an exposure surface for indirect prompt injection due to its recursive search and discovery phase.
- Ingestion points: External data retrieved from 10 or more search iterations as specified in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following directions found within retrieved search content.
- Capability inventory: The agent has the ability to write to the local file system (/mnt/agents/output/) and execute code via IPython.
- Sanitization: There are no explicit instructions for the agent to sanitize or validate the content retrieved from external sources before processing it.
Audit Metadata