us-market-sentiment
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the web via search tool results to evaluate market indicators. While the instructions do not specify explicit boundary markers or sanitization for this external content, the risk is categorized as safe because the skill's capabilities are limited to generating informational reports and recommendations without performing high-risk actions like file system modifications or external network posts of sensitive data.
- Ingestion points: Web search results retrieved during the assessment of the five core indicators (SKILL.md).
- Boundary markers: Absent in the instructions provided for processing search results.
- Capability inventory: Use of
web_search(SKILL.md). The skill lacks dangerous capabilities such as arbitrary code execution, file writes, or credential access. - Sanitization: No explicit sanitization or validation of search result content is required by the instructions.
Audit Metadata