smc-crt-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze external asset data and price action descriptions provided by the user. This creates an ingestion surface where an attacker could potentially embed malicious instructions within market data (e.g., hidden within price coordinates or asset descriptions). The risk is mitigated by the lack of dangerous capabilities available to the skill.
- Ingestion points: User-supplied asset data and price action descriptions provided in the chat context.
- Boundary markers: The instructions do not define specific delimiters for separating user-provided data from the agent's analysis logic.
- Capability inventory: The skill definition does not include any tools, scripts, or commands for file writing, network access, or subprocess execution.
- Sanitization: No explicit sanitization or validation of the input data is described in the provided rules.
- [SAFE]: The skill consists entirely of markdown-based rules and guidelines for financial analysis. It does not include any scripts, dependencies, or commands that interact with the host system, environment variables, or external network services.
Audit Metadata