The Agent Skills Directory

[SAFE]: The skill's primary functions—identifying and removing dead code—align with standard software engineering practices. No malicious code, external network calls, or unauthorized access patterns were detected.
[INDIRECT_PROMPT_INJECTION]: The skill's design involves reading and processing local source code and configuration files, creating a surface for indirect prompt injection if the processed files contain malicious instructions.
Ingestion points: The agent is instructed to read source code, configuration files, and documentation using grep and ast-grep tools (e.g., as described in SKILL.md and references/dead-config.md).
Boundary markers: No specific boundary markers are provided to separate codebase content from the agent's instructions, nor are there explicit directives to ignore embedded instructions in data.
Capability inventory: The skill utilizes file editing (Edit) and version control (git) capabilities to perform deletions and commits.
Sanitization: There is no evidence of sanitization or validation of the content read from the codebase before it is used to inform cleanup decisions.

cleanup-codebase