scholar-sidekick-api
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes curl to perform network requests to scholar-sidekick.com. These commands are used to transmit identifiers and bibliography data to the service and receive formatted citations or status reports.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by processing untrusted data from scholarly records and bibliography files. Ingestion points: Identifiers passed to text or id parameters; raw bibliography text passed to the bibliography parameter. Boundary markers: None explicitly defined in the instructions to prevent the agent from interpreting instructions within the returned citation data. Capability inventory: The agent has the capability to execute shell commands via curl and write output to files. Sanitization: No sanitization or validation of the content returned by the API is described.
- [EXTERNAL_DOWNLOADS]: The documentation references an optional setup path using npx -y scholar-sidekick-mcp@latest. This command downloads and executes a vendor-provided package from the npm registry at runtime.
Audit Metadata