obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands such as
findandgrepto search for files and text within the path/mnt/d/Obsidian Vault/AI Research/. These are standard utilities for file management and are used according to the skill's primary purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes markdown files from the local filesystem which could contain malicious instructions embedded by external sources.\n - Ingestion points: The agent reads note content and filenames during search and link analysis workflows (SKILL.md).\n
- Boundary markers: There are no specific instructions or delimiters defined to prevent the agent from following prompts found within the vault notes.\n
- Capability inventory: The agent has the ability to read from the filesystem and execute shell commands.\n
- Sanitization: The instructions do not specify any validation or sanitization for the content retrieved from the vault.
Audit Metadata