k2f-one-pager
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install a core dependency using the command
npx skills add suzheng/k2f. This resource is provided by the same author as the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data such as notes, specifications, or release details to generate document blueprints.
- Ingestion points: User-supplied text is ingested in Step 1 to create the
content_and_design.mdfile. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the user-provided data.
- Capability inventory: The skill is limited to creating markdown files and using the
k2fskill for document export; it does not have capabilities for network exfiltration or sensitive file system access. - Sanitization: The instructions do not specify any sanitization or validation for the ingested user content.
Audit Metadata