The Agent Skills Directory

[SAFE]: The skill follows its stated purpose of standardizing development environments. Its operations are limited to reading repository configuration files and generating text-based setup instructions.
[DATA_EXPOSURE]: The skill reads common project metadata files (e.g., package.json, go.mod, pyproject.toml) to infer required tool versions. This activity is restricted to public repository structure information and does not target sensitive user data, private keys, or environment secrets.
[COMMAND_EXECUTION]: The skill suggests standard setup commands like mise trust and mise install. These are presented as documentation for the user to execute manually and are not triggered automatically by the skill.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted repository data to generate its output, creating a potential surface for indirect prompt injection.
Ingestion points: Reads project manifest files such as package.json, requirements.txt, and go.mod (found in SKILL.md).
Boundary markers: None explicitly defined to separate untrusted file content from the agent's instructions.
Capability inventory: Generates configuration files (mise.toml) and suggests shell commands.
Sanitization: No specific sanitization or validation of the ingested repository data is mentioned before processing.

mise-configurator