The Agent Skills Directory

[SAFE]: The skill implements a disciplined debugging methodology focused on root-cause analysis and small, verified fixes. It uses standard file system and shell tools as expected for its software development purpose.
[PROMPT_INJECTION]: The skill processes untrusted data from the local codebase (source code, logs, and error traces) which represents a surface for indirect prompt injection.
Ingestion points: Uses Read, Grep, and Glob to examine project files and processes user-provided error symptoms.
Boundary markers: The skill does not explicitly define delimiters for code content or instructions to ignore embedded prompts in processed data.
Capability inventory: The skill has access to Bash, Write, and Edit, allowing for command execution and file modification.
Sanitization: There is no explicit sanitization of data read from files before it is processed by the agent.

hunt