The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external financial data, which constitutes a potential attack surface for indirect prompt injection.
Ingestion points: The skill instructions in SKILL.md specify input requirements including stock tickers, OHLCV price data, earnings growth figures, and relative strength metrics.
Boundary markers: No specific delimiters or boundary markers are defined to isolate untrusted data from the agent's instructions.
Capability inventory: The skill contains no executable scripts, shell commands, file-system write operations, or network exfiltration capabilities.
Sanitization: No input validation or sanitization mechanisms are implemented for the ingested data.
[NO_CODE]: The skill consists entirely of markdown documentation and configuration metadata. There are no associated scripts (.py, .js, .sh), binaries, or tool definitions that could perform actions on the host system.

minervini-vcp