revenue-engine-maturity-diagnostic
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external artifacts such as ICP documents, scoring models, and outreach sequences provided by the user during the diagnostic process. This ingestion surface is vulnerable to instructions embedded within those artifacts.
- Ingestion points: User-provided business artifacts (ICP documents, CRM duplicate counts, sequence logs, and meeting notes) described in
references/evidence-and-interview.md. - Boundary markers: Absent. There are no instructions for the agent to use specific delimiters or to disregard instructions found within the ingested evidence.
- Capability inventory: The skill instructions emphasize a "read-only" audit posture. There are no subprocess calls, network operations, or file-writing commands defined within the skill's scripts or instructions.
- Sanitization: Absent. The skill does not provide methods for escaping or validating the content of the analyzed artifacts.
- [NO_CODE]: The skill consists entirely of Markdown documentation and instructions. No executable scripts (.py, .js, .sh), configuration files, or binary assets are included, which significantly limits the risk of direct technical exploitation.
Audit Metadata