The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process external, untrusted code during the debugging cycle.
Ingestion points: External code files and bug descriptions provided at runtime (SKILL.md).
Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore instructions' warnings when processing input code.
Capability inventory: The skill orchestrates powerful tools including code-generator, test-generator, and error-analyzer (SKILL.md).
Sanitization: No sanitization or validation steps are defined to neutralize instructions that might be hidden in code comments or string literals within the target code.

hierarchical-debugger