The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and analyze various files within a target project directory, including AGENTS.md, README.md, and .grok/skills/*/SKILL.md. This represents an attack surface where a malicious project could embed instructions within these files to influence the auditor's scoring or behavior.
Ingestion points: Uses read_file and grep on project files like AGENTS.md, package.json, and others.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading untrusted project content.
Capability inventory: Has access to run_terminal_command, read_file, and list_dir.
Sanitization: No explicit sanitization or validation of the content of the read files is described before processing.
[COMMAND_EXECUTION]: The skill uses run_terminal_command to perform directory checks and git-related operations.
Evidence: Instructions suggest using ls, test -d, and git rev-parse --is-inside-work-tree to verify project status and hygiene.
Context: These commands are limited in scope and consistent with the stated purpose of auditing a repository.

project-auditor