The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands for auditing localization compliance, specifically running python3 scripts/localization_catalog.py check and utilizing rg (ripgrep) to identify hardcoded strings in source code files.
[INDIRECT_PROMPT_INJECTION]: The skill audits content from potentially untrusted external sources, such as pull request diffs and source code, creating a surface for indirect prompt injection. 1. Ingestion points: Pull request changes via git diff and file content from .swift, .ts, .tsx, and .md files. 2. Boundary markers: No delimiters or specific instructions to ignore embedded commands were identified. 3. Capability inventory: The skill has the ability to execute subprocesses (python3, rg, git) and read local files. 4. Sanitization: No sanitization or validation of the input strings was found.

cmux-localization