k2f-business-proposal
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions specify that the core engine should be installed using the command
npx skills add suzheng/k2f --skill k2f. This command downloads and installs additional capabilities from the vendor's own repository. Since the dependency belongs to the same author ('suzheng'), it is documented as a standard setup procedure for this workflow. - [INDIRECT_PROMPT_INJECTION]: The skill is intended to process external data sources such as discovery notes, RFP excerpts, and client briefs.
- Ingestion points: Discovery notes, RFP excerpts, and solution briefs provided by the user (as described in SKILL.md).
- Boundary markers: The skill focuses on narrative integrity and honesty in data representation but does not explicitly instruct the agent to use specific delimiters or to ignore potential instructions embedded within those source documents.
- Capability inventory: The skill uses a specialized 'k2f' tool for packing and exporting proposals. No dangerous command execution or network operations are directly performed by the instructions on the ingested data.
- Sanitization: The instructions do not define specific escaping or sanitization steps for external content before it is incorporated into the proposal blueprint.
Audit Metadata