strategy-critique
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions guiding the AI to perform a risk assessment. There are no scripts, binaries, or configuration files that execute commands.
- [NO_CODE]: No external dependencies, package installations, or remote code patterns were detected.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill does not access sensitive local files or perform network requests. It operates solely on the input provided during the conversation.
- [PROMPT_INJECTION]: While the skill uses strong instructional language (e.g., 'Assume the author is wrong'), this is functionally relevant to its stated purpose as a skeptical risk manager and does not attempt to bypass AI safety guidelines or extract system prompts.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided data (trading strategies). Although it lacks explicit boundary markers or sanitization, it does not possess any exploitable capabilities (like file writing or network access) that could be triggered by malicious input within a strategy description.
Audit Metadata