The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the sn command-line utility from the vendor's Homebrew tap located at github.com/Spot-Canvas/sn.
[COMMAND_EXECUTION]: Uses Bash to configure the sn utility and execute commands for subscribing to live signal streams and processing JSON output.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing data from an external signal stream.
Ingestion points: Live signal payloads received via sn signals in SKILL.md.
Boundary markers: No delimiters or safety instructions are specified for handling the contents of the signal payloads.
Capability inventory: The agent is expected to make trading decisions based on signal data and has the ability to execute network operations via curl.
Sanitization: There is no evidence of sanitization for natural language fields like reason or risk_reasoning, which could contain malicious instructions if the upstream signal provider is compromised.

signals