scholar-sidekick-python

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the scholar-sidekick package from PyPI, the official Python package registry, and optionally pandas to enable its core citation management features.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes metadata such as paper titles and retraction notices from external scholarly registries, which constitutes a vulnerability surface for indirect prompt injection. 1. Ingestion points: The verify, audit, and format methods in SKILL.md fetch content from the Scholar Sidekick REST API. 2. Boundary markers: The instructions do not provide explicit delimiters or guidance for the agent to ignore instructions embedded within the retrieved scholarly records. 3. Capability inventory: The skill is used within Python environments that often have access to the local file system and network. 4. Sanitization: The library does not appear to perform specific sanitization or filtering of fetched metadata before returning it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 11:39 PM
Security Audit — agent-trust-hub — scholar-sidekick-python