oldnavy-research

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Crawlora API (such as product descriptions and customer reviews) which could potentially contain malicious instructions aimed at the agent.
  • Ingestion points: Data retrieved from the Old Navy product reviews and search endpoints via the scripts/crawlora.sh helper script.
  • Boundary markers: None; the skill instructions do not currently include specific delimiters or directives for the agent to ignore instructions embedded within the retrieved product data.
  • Capability inventory: The skill can execute the scripts/crawlora.sh script to perform network operations and uses jq for parsing.
  • Sanitization: The skill relies on the API to return structured JSON data, but it does not explicitly sanitize text fields within that data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 02:44 AM
Security Audit — agent-trust-hub — oldnavy-research