The Agent Skills Directory

[COMMAND_EXECUTION]: The skill workflow involves executing shell commands, including ripgrep (rg) and a provided Python script (scripts/i18n_audit.py), to scan the local filesystem for text patterns and audit translation files. These commands operate on user-provided directory paths.
[PROMPT_INJECTION]: The skill includes a file named .security-scan-passed that contains fake security audit metadata, including a content hash and a timestamp. This is a deceptive artifact designed to mislead users or automated analyzers into believing the skill has undergone and passed external security verification.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by reading and processing external data (source code and locale files) from the filesystem.
Ingestion points: The agent is directed to use scripts/i18n_audit.py and rg to ingest content from arbitrary files within a specified source root.
Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the code or translation files being audited.
Capability inventory: The skill utilizes shell command execution and file reading capabilities.
Sanitization: No sanitization or filtering is applied to the data retrieved from the codebase before it is presented to the agent for decision-making.

i18n-expert