alphaxiv-paper-lookup

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes command-line tools to interact with external web endpoints.
  • Evidence: Uses curl -s in SKILL.md to fetch data from the alphaxiv.org domain.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves external data to provide paper summaries to the user.
  • Evidence: Fetches markdown files from https://alphaxiv.org/overview/{PAPER_ID}.md and https://alphaxiv.org/abs/{PAPER_ID}.md.
  • [PROMPT_INJECTION]: Potential surface for indirect prompt injection through untrusted external data.
  • Ingestion points: External markdown content is fetched from alphaxiv.org and interpreted by the agent (defined in SKILL.md).
  • Boundary markers: Absent. The skill does not use delimiters or instructions to ignore embedded commands in the fetched text.
  • Capability inventory: Network access via curl for data retrieval.
  • Sanitization: None detected. The skill assumes the fetched markdown is safe for consumption.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 12:12 PM