The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool but restricts its usage to safe, non-interactive commands (mktemp, mkdir, and date) through the allowed-tools frontmatter configuration.
[DATA_EXFILTRATION]: The skill utilizes WebSearch and WebFetch for its core function of researching user-provided topics. No unauthorized network requests or patterns of credential theft were identified.
[PROMPT_INJECTION]: The skill processes untrusted data from the web via its retrieval tools. This creates an indirect prompt injection surface typical for research agents. However, the skill acts primarily as an orchestrator and lacks evidence of malicious intent or safety bypass instructions.

storm-generate