The Agent Skills Directory

[SAFE]: The skill's content is purely instructional, focusing on formatting and content standards for financial reporting. No malicious patterns such as obfuscation, remote code execution, or privilege escalation were identified.
[PROMPT_INJECTION]: The skill mentions reading external data files, specifically metrics.csv and equity.csv, to populate backtest reports. While this introduces an ingestion point for untrusted data (Indirect Prompt Injection surface), the skill does not utilize any high-risk tools, shell commands, or network operations that could be exploited via such an injection, maintaining a safe profile.

report-generate