risk-reward-sanity-check
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied data, including entry points, stop-loss levels, and trade theses. This constitutes an attack surface for indirect prompt injection. However, the skill does not possess capabilities such as network access, file system modification, or shell command execution, which significantly mitigates the risk. The skill lacks explicit boundary markers or sanitization for this input.
- Ingestion points: User-provided trade parameters (direction, entry, stop, targets, thesis) defined in SKILL.md.
- Boundary markers: None identified.
- Capability inventory: The skill is limited to text analysis and local mathematical calculations; no subprocess, network, or file-write capabilities are requested or used.
- Sanitization: None identified.
- [DYNAMIC_EXECUTION]: The skill references a local Python library located at
skills/_lib/calculations.pyfor mathematical helper functions. This is a standard modular architecture for agent skills and does not involve remote code downloading or runtime code generation.
Audit Metadata