The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill uses user-supplied arguments directly within a shell command, creating a surface for indirect prompt injection or command injection attacks.
Ingestion points: The $ARGUMENTS variable in SKILL.md receives input intended for the export format.
Boundary markers: There are no boundary markers or instructions to the agent to sanitize or treat the arguments strictly as a format string.
Capability inventory: The skill uses the Bash tool to execute a Node.js process (node ${CLAUDE_PLUGIN_ROOT}/src/export.js $ARGUMENTS).
Sanitization: No input validation or sanitization logic is present in the skill instructions to prevent shell metacharacter injection.

cco-export