The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts including isms_audit_scheduler.py, audit_simulator.py, and cross_framework_mapper.py to process compliance data.
[DATA_EXPOSURE]: The skill accesses local JSON files such as audit_scope.json and program.json which may contain sensitive organizational information.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting external data files while having command execution capabilities.
Ingestion points: Untrusted data enters via audit_scope.json, iso27001_scope.json, and program.json as seen in the Workflow section of SKILL.md.
Boundary markers: Absent; there are no delimiters or explicit instructions to ignore embedded commands within the ingested JSON files.
Capability inventory: The skill utilizes python subprocess calls to execute multiple scripts located within the local repository structure.
Sanitization: Absent; the skill does not specify validation or sanitization routines for the content of the data files before they are processed by the scripts.

iso27001-audit-prep