The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides capabilities to launch and attach to local binaries via the LLDB debugger.
Evidence: Found process launch and process attach commands in SKILL.md which utilize the LLDB API to manage process execution.
[COMMAND_EXECUTION]: The skill enables the evaluation of dynamic expressions within a running process context.
Evidence: Found the expr command in SKILL.md intended for evaluating expressions in the current frame.
[EXTERNAL_DOWNLOADS]: The skill installs a vendor-owned package from a public registry.
Evidence: The install field in SKILL.md specifies pip install cli-anything-lldb.
[PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection through process introspection.
Ingestion points: frame locals, thread backtrace, and memory read commands in SKILL.md.
Boundary markers: None identified in the provided instructions.
Capability inventory: The skill can launch processes and evaluate expressions (process launch, expr).
Sanitization: No explicit sanitization or filtering of debugged process data is mentioned.

cli-anything-lldb