The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests data from external skill files.
Ingestion points: The agent is instructed to use view_file on SKILL.md files in the .agent/skills directory to understand their specific standards (SKILL.md, Section 1).
Boundary markers: There are no instructions to use delimiters or warnings to ignore potentially malicious instructions within those external files.
Capability inventory: The skill possesses significant capabilities, including run_command and write_to_file, which could be triggered if the agent follows instructions found inside the scanned skill files.
Sanitization: No validation or sanitization of the content from the external files is performed before it is processed by the agent.

planner