openclaw-research-paper-push-skill

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PERSISTENCE]: The skill uses cron scheduling, including platform-specific support and system crontab instructions, to ensure the automated paper alerts run at scheduled times across sessions.
  • [INDIRECT_PROMPT_INJECTION]: The skill generates summaries from research papers fetched from the OpenAlex API, which creates a surface where malicious content in academic metadata could theoretically influence agent behavior.
  • Ingestion points: Research paper metadata retrieved from the OpenAlex API (SKILL.md).
  • Boundary markers: None identified in the documentation to delimit external API content.
  • Capability inventory: The skill maintains local state by writing to the data/ directory, performs network requests to academic sources, and schedules tasks via cron (SKILL.md).
  • Sanitization: No explicit sanitization or filtering of external API data is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 06:50 PM
Security Audit — agent-trust-hub — openclaw-research-paper-push-skill