paper-index
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted metadata from markdown files within the
papers/notes/directory to dynamically generate Obsidian.baseconfiguration files. - Ingestion points: Metadata fields such as
title,tags, andtldrare extracted from notes inpapers/notes/*.md. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from interpreting instructions embedded within the paper metadata.
- Capability inventory: The skill requires file reading and file writing capabilities within the user's Obsidian vault.
- Sanitization: The skill does not specify any sanitization, filtering, or validation of the extracted data before it is interpolated into the generated YAML templates.
Audit Metadata