reading-guide
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from academic PDFs and Zotero library files, creating a vulnerability where instructions embedded in a paper could influence the agent's actions.
- Ingestion points: PDF content extracted via pymupdf and data from Zotero library.json.
- Boundary markers: The instructions do not define specific delimiters or warning prompts to ignore instructions within the processed text.
- Capability inventory: The skill has the capability to write markdown files to the local file system in the Obsidian vault's Guides folder.
- Sanitization: There is no explicit requirement to sanitize, escape, or filter the extracted text before it is processed by the model.
Audit Metadata