The Agent Skills Directory

[SAFE]: The skill consists of pedagogical documentation for Godot engine developers. It covers syntax errors, runtime crashes, and performance optimization using standard best practices.
[SAFE]: All provided code samples are benign GDScript snippets. No obfuscation, hidden commands, or suspicious network activities were found.
[SAFE]: The requested tools in the frontmatter, including Bash and file system access, are appropriate for a technical debugging assistant tasked with analyzing project files and logs.
[INDIRECT_PROMPT_INJECTION]: The skill operates by analyzing user-provided code and error logs, which introduces an ingestion surface for untrusted data.
Ingestion points: The agent reads project files and error messages using tools like Read and Grep.
Boundary markers: There are no explicit instructions for the agent to use delimiters when processing external code.
Capability inventory: The skill has access to file modification (Write, Edit) and shell execution (Bash) tools.
Sanitization: No explicit sanitization of ingested content is defined in the instructions.
Note: This surface is an inherent part of the skill's primary function as a debugging assistant and is handled within the agent's standard operational parameters.

godot-debugging