Semantic Scholar Lookup

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation process fetches and installs the asta CLI tool directly from the author's official GitHub repository at github.com/allenai/asta-plugins.git.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it retrieves untrusted third-party data from the Semantic Scholar API.
  • Ingestion points: Metadata, abstracts, and full-text snippets retrieved via asta papers search, asta papers get, and asta papers snippet-search (found in SKILL.md).
  • Boundary markers: None identified; external content is interpolated directly into the agent's context.
  • Capability inventory: The agent has access to the Bash tool with asta papers * commands, which can be used to further query the API or process data with jq.
  • Sanitization: No evidence of sanitization or filtering of the retrieved paper content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 10:38 PM