The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access behaviors were detected during the analysis. The skill functions as an informational tool for traders.- [INDIRECT_PROMPT_INJECTION]: The skill fetches signals and market data from an external API (signals.x70.ai), which represents a potential attack surface for indirect instructions. However, the risk is negligible as the skill lacks dangerous tools and primarily processes structured data.
Ingestion points: Signals and statistics are retrieved from the vendor's API endpoints at https://signals.x70.ai/api/skill/ (SKILL.md).
Boundary markers: No explicit delimiter markers or "ignore instructions" warnings are used when processing the API responses.
Capability inventory: The skill is restricted to fetching and presenting data; it does not have tools for file system access, shell command execution, or other high-privilege operations.
Sanitization: The skill does not describe specific sanitization of text fields (like 'reasoning' or 'summary') returned by the remote service.- [EXTERNAL_DOWNLOADS]: The skill instructions provide configuration steps for connecting to an external MCP server at https://signals.x70.ai. This is the intended delivery mechanism for the skill's functionality and is considered a safe operational requirement.

trading-signals