knowledge-management
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external research and literature notes to generate atomic Zettelkasten cards, creating a surface where instructions hidden in the processed documents could potentially influence agent behavior.
- Ingestion points: Processes content from academic papers, Zotero entries, and literature notes stored in the sources directory.
- Boundary markers: The workflows do not specify the use of delimiters or instructions for the agent to ignore potential commands embedded within the source material.
- Capability inventory: The skill uses Read, Write, Glob, and Grep tools, allowing it to modify the filesystem within the user's knowledge vault.
- Sanitization: No sanitization or validation of the input content is mentioned before it is processed and incorporated into the knowledge base.
Audit Metadata