openclaw-research-paper-push-skill

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches academic paper metadata from the OpenAlex API and is distributed via a public GitHub repository. Both are legitimate and well-known services relevant to the skill's academic purpose.
  • [COMMAND_EXECUTION]: Utilizes a Python script (scripts/manage_papers.py) and optional curl commands to query academic databases and manage local subscription configurations.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external research paper titles and abstracts from the OpenAlex API to generate summaries.
  • Ingestion points: Research paper metadata retrieved from the OpenAlex API.
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: Generates summaries and sends notifications to a recipient ID.
  • Sanitization: No explicit sanitization or filtering of external content is documented.
  • [DATA_EXFILTRATION]: Data management is handled locally through JSON files in a data/ directory. No unauthorized transmission of sensitive system files or user credentials was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 08:47 AM
Security Audit — agent-trust-hub — openclaw-research-paper-push-skill