getnote-kb
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
getnoteandgnoteCLI tools to perform operations such as managing knowledge bases, adding or removing notes, and organizing directories. These commands interact directly with the local environment to manage the service's data.\n- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by ingesting and processing content from untrusted external sources.\n - Ingestion points: The skill retrieves full-text content from Douyin bloggers and live stream transcripts via the
blogger-contentandlivecommands (file: SKILL.md).\n - Boundary markers: The instructions do not specify any delimiters or boundary markers to differentiate external data from agent instructions, nor do they include warnings to ignore instructions embedded in the fetched content (file: SKILL.md).\n
- Capability inventory: The agent has the capability to write to knowledge bases, create or delete directories, and manage subscriptions based on processed data (file: SKILL.md).\n
- Sanitization: No sanitization or validation of the retrieved external content is required or described in the instructions (file: SKILL.md).
Audit Metadata