expansion-opportunity-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill processes data from external business systems to generate analysis and draft communications. While this involves ingesting untrusted data, the design incorporates several security best practices. (1) Ingestion points: Untrusted data enters the agent context from user-defined CRM, Billing, and Usage sources as described in SKILL.md. (2) Boundary markers: The skill does not use explicit delimiters to separate external data from its own instructions. (3) Capability inventory: The skill focus is on analysis and drafting; no dangerous capabilities such as arbitrary command execution, file system modifications, or direct network exfiltration are present in the provided files. (4) Sanitization: There is no specific validation or sanitization of the input data from the external sources. (5) Risk Mitigation: The potential for indirect prompt injection is mitigated by the explicit 'Never auto-send' policy, which requires a human to approve all drafted outreach before it is delivered.
- [NO_CODE]: The skill package contains only Markdown instructional and reference files. It does not include any executable scripts, binaries, or shell commands.
Audit Metadata