The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The skill ingests DBC files (SKILL.md) for signal definitions and message management.
Boundary markers: There are no defined boundary markers or instructions to treat data within DBC files as literal or non-executable.
Capability inventory: The skill enables access to Bash and file system modifications (Write, Edit), creating a capability chain where instructions extracted from data could lead to unauthorized system operations.
Sanitization: No sanitization, schema validation, or escaping of DBC content is specified before the data is processed or used in operations.

can-bus