business-consultant
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied business context (name, stage, market, revenue) to generate strategic reports.
- Ingestion points: User input provided as arguments to the
/business-consultantcommand inSKILL.md. - Boundary markers: Absent; user input is interpolated into the prompt templates defined in
templates/prompt-main.md. - Capability inventory: None; the skill does not use any tools for network access, file system modification, or command execution.
- Sanitization: Absent; the skill relies on the underlying model's safety guardrails to handle potentially malicious input.
- [DATA_EXPOSURE]: The skill instructions in
README.mdandSKILL.mdencourage users to provide real revenue and cost data to improve forecast accuracy. While there are no network exfiltration patterns in the skill, users should be aware that they are sharing sensitive financial information with the AI agent.
Audit Metadata