Asta Literature Reports

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill is configured to use specific CLI tools (asta literature find, asta papers, and jq) for retrieving and processing academic data. These tools are restricted to their functional scope within the allowed-tools configuration, following the principle of least privilege.
  • [EXTERNAL_DOWNLOADS]: Academic metadata and paper snippets are fetched from external repositories (such as Semantic Scholar or ArXiv) via the asta CLI. These operations are core to the skill's purpose and originate from a trusted vendor source.
  • [PROMPT_INJECTION]: As the skill ingests untrusted external content (academic papers), it is theoretically susceptible to indirect prompt injection. However, the potential impact is mitigated by the restricted execution environment, which only allows writing markdown files to a specific directory (.asta/literature/report/).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 05:44 AM