nice-lark-doc
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs necessary official CLI tools and agent extensions.
scripts/setup.shinstalls the@larksuiteoapi/clipackage globally via npm.- The setup script also uses
npx skills addto fetch and install skills from thelarksuite/clirepository. - [COMMAND_EXECUTION]: Shell scripts are employed for dependency management and environment verification.
scripts/setup.shandscripts/check-deps.shexecute commands likenpm install,npx skills, andlark-cli auth statusto ensure the runtime environment is properly configured.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content which presents a potential injection surface.
- Ingestion points: The skill reads existing content from Lark documents provided by the user during the 'Beautify' workflow (specified in
SKILL.md). - Boundary markers: Absent. The skill does not explicitly use delimiters to separate user content from system instructions in its prompt generation logic.
- Capability inventory: Includes the ability to create and update Lark documents and manage whiteboards via
lark-clisubprocess calls. - Sanitization: Absent. Content is reformatted according to style recipes (e.g.,
editorial-clean.md) without explicit sanitization of embedded instructions.
Audit Metadata