schloss-cigar-butt
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of Markdown files that provide guidance for investment analysis. There are no executable scripts, shell commands, or network operations defined in the skill logic.
- [NO_CODE]: No programming code (Python, JavaScript, etc.) or binary executables are included in the skill package.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it is designed to ingest and process external financial data.
- Ingestion points: Assets, financial data, and market regime data are ingested through context inputs defined in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the source data.
- Capability inventory: The skill lacks any high-risk capabilities; it does not request tool access for file writing, shell execution, or network communication.
- Sanitization: No sanitization or validation logic is specified for the external data inputs.
Audit Metadata