The Agent Skills Directory

[SAFE]: The skill implementation is transparent and relies entirely on Python's built-in modules, avoiding supply-chain risks from unverified third-party packages.\n- [SAFE]: No hardcoded credentials, sensitive local file access (such as SSH keys or environment files), or persistence mechanisms were detected in the codebase.\n- [EXTERNAL_DOWNLOADS]: The script scripts/bibtex_fetch.py performs network requests to established academic platforms (export.arxiv.org and api.semanticscholar.org). These operations are restricted to fetching metadata for the purpose of generating BibTeX entries and do not involve remote code execution or exfiltration of private data.\n- [COMMAND_EXECUTION]: The commands defined in the skill are for executing the provided Python script with user-supplied arguments (arXiv IDs or search titles). The script uses standard parsing and basic regex to handle these inputs, with no evidence of shell injection vulnerabilities or unauthorized privilege escalation.

bibtex-fetch