k2f-aesthetic-ms-word
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install a companion dependency (
suzheng/k2f) vianpx skills add. This resource is maintained by the same author as the skill itself. - [COMMAND_EXECUTION]: The workflow involves running tool-specific commands such as
pack,verify, andexportusing thek2futility to compile and generate the final document deliverable. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data, such as drafts and Markdown files, to create structured documents. This introduces a surface where malicious instructions in the input could attempt to influence the agent's behavior.
- Ingestion points: User-provided briefs, messy drafts, and Markdown content as described in the Workflow section of
SKILL.md. - Boundary markers: No specific boundary markers or 'ignore instructions' delimiters are defined to separate user content from the agent's layout logic.
- Capability inventory: The skill utilizes
npxfor dependency management and a command-line tool (k2f) for packaging and exporting files to the DOCX format. - Sanitization: There are no documented sanitization or validation steps for the input content before it is parsed by the design engine.
Audit Metadata