The Agent Skills Directory

[SAFE]: Analysis of the skill's instructions and scripts indicates that the functionality is entirely focused on infrastructure security hardening and auditing. No malicious intent, obfuscation, or unauthorized data access patterns were detected.
[COMMAND_EXECUTION]: The skill includes a bash script (scripts/audit-infrastructure.sh) designed to perform local security checks. It utilizes standard system utilities such as grep, env, stat, and netstat to inspect environment variables, file permissions, and network listeners. These operations are performed locally and results are printed to the console for the user's review.
[DATA_EXPOSURE]: The audit script scans local environment variables for common secret-related keywords (e.g., api_key, password) to alert the user of potential exposures. This is a standard security auditing practice and does not involve the exfiltration of sensitive data to external servers.
[INDIRECT_PROMPT_INJECTION]: The skill defines a strict input_schema for its operations, using enumerations for assessment_scope and environment. This design significantly reduces the attack surface for indirect prompt injection by ensuring that the agent only processes well-defined, safe input values.

infrastructure-security