sector-rotation-detector
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions, strategy frameworks, and report templates. No scripts, binaries, or automated shell commands are present.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information regarding portfolio holdings and investment preferences, which constitutes a standard vulnerability surface for indirect prompt injection. However, this interaction is a primary requirement for its analytical function and no malicious patterns were identified.
- Ingestion points: User-provided market scope, existing holdings, and risk preferences defined in the 'Working Flow' section of SKILL.md.
- Boundary markers: No specific delimiters or safety instructions are used to isolate user-provided data from the analysis logic.
- Capability inventory: The skill suggests the use of a financial data toolkit ('findata-toolkit-cn') for read-only market data retrieval.
- Sanitization: Not applicable for this non-executable instruction set.
Audit Metadata