openlibrary

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides structured access to the Open Library catalog. Analysis of the CLI script and documentation confirms it only performs read-only metadata lookups via HTTP GET requests to openlibrary.org and covers.openlibrary.org. No credentials, sensitive file access, or command execution patterns were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which serves as a potential surface for indirect prompt injection.\n
  • Ingestion points: The script scripts/openlibrary retrieves titles, author biographies, and book descriptions from the community-edited Open Library wiki.\n
  • Boundary markers: No explicit delimiters are specified for the agent when it interpolates retrieved metadata into its context.\n
  • Capability inventory: The skill is limited to network GET requests and terminal output; it lacks file-write or shell-execution capabilities.\n
  • Sanitization: Data is parsed as JSON, but the script does not filter for potential prompt injection characters in the text fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:58 PM
Security Audit — agent-trust-hub — openlibrary