The Agent Skills Directory

[COMMAND_EXECUTION] (HIGH): The skill allows the use of the Bash tool without any safety constraints or sandboxing. This provides a direct path for executing arbitrary shell commands on the host environment.
[PROMPT_INJECTION] (HIGH): The skill is susceptible to Indirect Prompt Injection (Category 8) because it processes untrusted data and possesses high-privilege capabilities. Ingestion points: The agent reads project files using Read, Glob, and Grep tools. Boundary markers: Absent; there are no instructions to delimit input or ignore instructions found within files. Capability inventory: The agent can modify the filesystem using Write and Edit, and execute code via Bash. Sanitization: Absent; the skill does not specify any validation or sanitization of ingested content before it is used in tool calls or code generation.

frontend-hook