sn-search-academic

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from well-known and trusted academic platforms, including ArXiv, Semantic Scholar, NCBI (PubMed/PMC), and Wikipedia. These operations are core to the skill's purpose and target official API endpoints.
  • [CREDENTIALS_UNSAFE]: The scripts are designed to handle API keys through command-line arguments or environment variables (e.g., S2_API_KEY). This is a standard and safe practice for secret management, avoiding hardcoded credentials.
  • [DATA_EXFILTRATION]: There is no evidence of local data exfiltration. Network requests are limited to the aforementioned academic services and are used solely to retrieve information requested by the user.
  • [COMMAND_EXECUTION]: The skill does not execute arbitrary shell commands or use dynamic execution functions like eval() or exec().
  • [PROMPT_INJECTION]: The skill instructions in SKILL.md are focused on usage guidelines and do not contain any attempts to override or bypass AI safety constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 09:37 AM