resale-secondhand-research

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill communicates exclusively with its own infrastructure at api.crawlora.net. As the vendor's own API, this represents standard and expected functionality for a research skill.
  • [SAFE]: Security best practices are followed for credential management. The skill instructs users to store the CRAWLORA_API_KEY in an environment variable rather than hardcoding it.
  • [SAFE]: The primary execution logic resides in scripts/crawlora.sh, which is a straightforward wrapper for curl. It utilizes bash arrays and proper quoting to safely handle arguments and prevents common shell injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: As the skill fetches and processes user-generated content from external marketplaces (listing descriptions, shop bios, etc.), it possesses an attack surface for indirect prompt injection.
  • Ingestion points: Data enters the agent context through the output of scripts/crawlora.sh in reference/endpoints.md and SKILL.md.
  • Boundary markers: None present; the agent processes the raw JSON output from the API.
  • Capability inventory: The skill has permissions to execute shell commands and read files.
  • Sanitization: No specific filtering or sanitization of marketplace content is performed before the data is returned to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 06:52 PM
Security Audit — agent-trust-hub — resale-secondhand-research