literature-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no malicious code, obfuscation, or unauthorized network activity. All functionality is aligned with its stated purpose of assisting researchers in summarizing academic papers.\n- [INDIRECT_PROMPT_INJECTION]: The skill acts as a text-processing interface for external data, creating an attack surface for indirect prompt injection.\n
- Ingestion points: The skill processes user-provided academic papers, abstracts, and highlights in SKILL.md.\n
- Boundary markers: The instructions lack explicit delimiters to isolate the source text or directives to ignore instructions that might be embedded within the academic papers.\n
- Capability inventory: The skill utilizes connected note-taking tools or the Scratchpad connector (a vendor-owned resource) to save generated content, representing a managed file-writing capability.\n
- Sanitization: There are no specific instructions to sanitize or validate the content of the academic papers before processing.
Audit Metadata