The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted LLM outputs, creating a vulnerability surface for indirect prompt injection.
Ingestion points: The output parameter in diagnose_failure and debug_llm_output functions in SKILL.md.
Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the processed text.
Capability inventory: The skill uses processed data for regex searches, JSON parsing, and string interpolation into new prompts.
Sanitization: No sanitization or filtering is performed on external content before it is processed or interpolated.

llm-debugger