archive-to-brain
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
obsidianCLI command (obsidian create) to save notes. This involves executing shell commands with variables derived from conversation content. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted conversation history.
- Ingestion points: Reads the entire conversation history to generate summaries (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat conversation content as untrusted data during interpolation.
- Capability inventory: The skill can execute shell commands via the Obsidian CLI and perform direct file system writes (SKILL.md).
- Sanitization: There is no evidence of sanitization or escaping logic for the
{{filename}}or{{full content}}variables before they are used in shell commands.
Audit Metadata