biz-dev-proposal
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses clear, instructional language for document generation and does not contain any patterns intended to override agent behavior, bypass safety filters, or extract system prompts.
- [DATA_EXFILTRATION]: While the skill requests business-related inputs (client names, pricing), it lacks any network capabilities, such as
curlorwgetcommands, and does not access sensitive local file paths. - [REMOTE_CODE_EXECUTION]: There are no scripts, binaries, or instructions to install external packages in either the
SKILL.mdor the referenced framework file. - [COMMAND_EXECUTION]: The workflow is entirely based on natural language generation within the agent's environment and does not involve the execution of shell commands or system-level operations.
- [SAFE]: All content, including referenced business frameworks like the NOSE structure and Kahan's Scorecard, is consistent with the stated purpose of generating business proposals.
Audit Metadata