invest-enterprise
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script at
~/.agents/skills/mx-data/scripts/get_data.py. This command is used to fetch enterprise metrics such as revenue, profit, and debt ratios. This is a standard operational pattern for skills within this environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external enterprise sources. This creates a potential surface for indirect prompt injection if the retrieved data contains malicious instructions.
- Ingestion points: Enterprise metrics retrieved via the
get_data.pyscript (SKILL.md). - Boundary markers: None explicitly defined in the skill instructions.
- Capability inventory: Subprocess execution of local Python scripts (SKILL.md).
- Sanitization: No specific sanitization or validation steps are mentioned for the retrieved metrics before they are inserted into the output template.
Audit Metadata