ebay-research

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process untrusted external data from eBay.
  • Ingestion points: External data enters the agent context through eBay search results, item details, and seller feedback endpoints as described in SKILL.md and reference/endpoints.md.
  • Boundary markers: Absent. The skill does not provide specific delimiters or instructions to the agent to disregard instructions potentially embedded in the retrieved eBay listings or reviews.
  • Capability inventory: The skill includes scripts/crawlora.sh, which performs network operations using curl to reach the API.
  • Sanitization: Absent. There is no evidence of filtering or sanitization applied to the external content before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill utilizes a shell script, scripts/crawlora.sh, which executes curl commands to interact with the vendor's API. This is a functional component necessary for the skill's operation but represents a command execution capability that targets the api.crawlora.net domain.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 06:10 PM
Security Audit — agent-trust-hub — ebay-research