chat-to-obsidian-note
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
create_filetool to save generated technical documentation and update index files within a local directory structure atD:\Documents\Knowledge Base\Readme\. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted chat history to generate notes. 1. Ingestion points: Technical chat transcripts (SKILL.md). 2. Boundary markers: Absent; there are no specific delimiters or instructions to the agent to ignore instructions embedded within the chat data. 3. Capability inventory: Uses
create_fileto write and update Markdown files (SKILL.md). 4. Sanitization: Partial; Step 3.4 in SKILL.md instructs the agent to avoid special characters in filenames, though no content-level sanitization is mentioned.
Audit Metadata