The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill interpolates the $ARGUMENTS variable directly into a workflow pipeline. This represents a potential surface for indirect prompt injection or command injection as user-supplied content is passed to tools without sanitization.
Ingestion points: User input enters the system via the $ARGUMENTS variable in SKILL.md.
Boundary markers: There are no boundary markers or instructions to ignore embedded commands within the interpolated content.
Capability inventory: The skill is granted access to the Bash(git:*), Read, and Write tools.
Sanitization: No sanitization or validation of the input is performed before interpolation.

start-hotfix