lark-minutes
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands via the
lark-clibinary. This involves passing user-provided parameters such as search queries, tokens, and file paths directly to the CLI tool. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted content (e.g., meeting titles, summaries, and transcripts) from Lark APIs. Malicious instructions embedded in this data could potentially influence the agent's behavior.
- Ingestion points: Search results and metadata fetched via
lark-cli minutes +searchandlark-cli minutes minutes get(as documented inSKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when processing retrieved data.
- Capability inventory: The agent has file system write access through the
lark-cli minutes +download --output <path>command (as documented inreferences/lark-minutes-download.md). - Sanitization: No explicit sanitization or validation of the retrieved text content is defined in the skill logic.
Audit Metadata