obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use specific bash workflows, including
findandgrepcommands, to search and manipulate files within a designated local directory. - [PROMPT_INJECTION]: The skill reads and processes external data (Obsidian notes), which constitutes a surface for indirect prompt injection attacks.
- Ingestion points: The agent processes markdown files (.md) located in the directory path
/mnt/d/Obsidian Vault/AI Research/specified in SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded directives are provided for the content being processed.
- Capability inventory: The agent has the ability to execute shell commands (find/grep) and read file contents across the specified vault.
- Sanitization: No sanitization or validation logic is defined for the content extracted from the markdown notes.
Audit Metadata