alterlab-citation-graph

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to api.openalex.org to retrieve academic metadata. OpenAlex is a well-known, public repository of scholarly data. The communication is handled using Python's standard urllib library with appropriate URL encoding and timeouts.
  • [COMMAND_EXECUTION]: The provided Python script scripts/build_graph.py is intended to be run locally. It uses argparse for secure command-line argument handling and does not invoke subshells or execute arbitrary user-supplied strings as code.
  • [DATA_EXPOSURE]: The skill does not access sensitive local files or environment variables beyond the optional OPENALEX_MAILTO for API etiquette. It does not require or use API keys. Output is written to user-specified local paths in standard GraphML and JSON formats.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes external data (academic paper titles and metadata from OpenAlex), this data is used to construct a structured graph file and is not interpolated into the agent's system prompt in a way that could influence agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:28 PM
Security Audit — agent-trust-hub — alterlab-citation-graph