The Agent Skills Directory

[SAFE]: The skill is designed for process documentation and management. It does not exhibit malicious behaviors such as data exfiltration, privilege escalation, or unauthorized network access.
[COMMAND_EXECUTION]: The skill utilizes standard system utilities like grep and date to facilitate its auditing and logging workflows. These operations are scoped to the local environment and intended documentation tasks.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests content from existing SOP files during the audit process, the risk is minimal as the data is used for documentation consistency checks. Ingestion points: SOP files within the docs/sop/ directory; Boundary markers: Absent; Capability inventory: Local filesystem access (list, read, write) and shell utility execution; Sanitization: No explicit sanitization of audited markdown content.
[DATA_EXPOSURE]: The skill prompts users to identify inputs needed for processes (e.g., credential names) but does not attempt to access or exfiltrate sensitive values, focusing only on metadata for documentation.

sop