strategy-critique
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze trading strategy descriptions provided by the user, which creates a surface for indirect prompt injection where malicious instructions could be embedded in the strategy text to influence the agent's behavior.
- Ingestion points: The agent is instructed to work through adversarial questions based on a trading strategy provided in the context (implied user input).
- Boundary markers: Absent. There are no delimiters or specific instructions to ignore embedded commands within the strategy being critiqued.
- Capability inventory: None. The skill (SKILL.md) does not define any subprocess calls, file writes, network operations, or tool invocations.
- Sanitization: Absent. There is no logic provided to filter or escape the input strategy text.
Audit Metadata