The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override system behavior, bypass safety filters, or extract system prompts were detected.- [DATA_EXFILTRATION]: No network operations, hardcoded credentials, or sensitive file access patterns are present in the skill instructions or metadata.- [REMOTE_CODE_EXECUTION]: The skill contains no executable scripts, shell commands, or external package dependencies.- [OBFUSCATION]: No hidden content, encoded strings, homoglyphs, or zero-width characters were identified in any of the files.- [INDIRECT_PROMPT_INJECTION]: The skill ingests external financial market data (OHLCV) which is an ingestion point for untrusted data. However, the skill lacks any capabilities to perform dangerous actions (such as file writes or network requests) based on that data, presenting a negligible risk surface.

darvas-box