ecommerce-walmart-keyword-research
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from an external marketplace research API, creating a surface for indirect prompt injection where malicious instructions might be embedded within product or keyword data.
- Ingestion points: Untrusted data enters the agent's context via the output of
scripts/sorftime_walmart_keyword_research.py, which fetches JSON responses fromapi.nexscope.ai. - Boundary markers: The instructions in
SKILL.mdattempt to mitigate this by directing the agent to 'Summarize only returned facts' and 'Distinguish the NexScope transport envelope from the inner business response'. - Capability inventory: The skill enables network access to vendor endpoints and local filesystem writes to the
nexscope/directory viascripts/sorftime_walmart_keyword_research.py. - Sanitization: While the script parses JSON, it does not sanitize the text content for potential LLM instructions before it is presented to the agent.
Audit Metadata