obsidian-common-errors
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool for tasks such as
npm run buildand checking file existence withls -la. These operations are performed within the local plugin development directory to verify build artifacts. - [EXTERNAL_DOWNLOADS]: The documentation suggests installing the
obsidian-hot-reloadpackage vianpm. This is a standard utility in the Obsidian developer community for accelerating the development cycle. - [PROMPT_INJECTION]: The skill provides instructions for analyzing external plugin source code, which constitutes a surface for indirect prompt injection. Maliciously crafted comments or code in the target plugin could attempt to influence the agent's diagnostics.
- Ingestion points: Uses
ReadandGreptools to inspect local plugin files. - Boundary markers: The instructions do not define specific delimiters for separating the analyzed code from the agent's diagnostic prompts.
- Capability inventory: The skill has access to the
Bashtool (node-related commands),Read, andGrepcapabilities. - Sanitization: No explicit sanitization or validation of the ingested code content is specified.
Audit Metadata