The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection through user-supplied input.
Ingestion points: User requests containing triggers like "timeout handler" or "timeout" are processed by the skill as described in SKILL.md.
Boundary markers: The instructions do not define any delimiters or specific guardrails to help the agent distinguish between user data and its own operational instructions.
Capability inventory: The skill is configured with broad capabilities including Bash(cmd:*), Write, and Edit as listed in the allowed-tools section of SKILL.md.
Sanitization: There is an absence of instructions for the agent to sanitize, validate, or escape content provided in user requests before performing actions or generating code.

timeout-handler