The Agent Skills Directory

[SAFE]: The skill provides structured guidance for security log analysis, mapping events to MITRE ATT&CK techniques and following NIST SP 800-92 recommendations for log management and baseline establishment.
[PROMPT_INJECTION]: The skill includes a 'Prompt Injection Safety Notice' (Section 8) that explicitly instructs the agent to treat all analyzed content as data rather than instructions. It specifically commands the agent to ignore any embedded directives like 'ignore this event' or 'run the following command' found within log entries.
[DATA_EXFILTRATION]: The skill explicitly mandates the redaction of sensitive values, including passwords, session tokens, and private keys, from the final analysis report. It also limits the use of internal IP addresses to only what is strictly necessary for the analysis objective.
[EXTERNAL_DOWNLOADS]: The skill references established documentation from trusted organizations and well-known services, including NIST (csrc.nist.gov), MITRE (attack.mitre.org), Microsoft (learn.microsoft.com), and Amazon Web Services (docs.aws.amazon.com). These references are for documentation purposes and do not involve remote code execution.
[COMMAND_EXECUTION]: The skill is restricted via its frontmatter configuration to the 'Read', 'Grep', and 'Glob' tools. It explicitly forbids the execution of commands or scripts found within analyzed log data, such as PowerShell script blocks or CLI arguments captured in events.

log-analysis