The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted TOML files from the project workspace, which represents a potential attack surface for instructions embedded in data.
Ingestion points: The skill reads .toml files and project-specific configuration files during the taplo lint and taplo format steps.
Boundary markers: The skill does not define specific delimiters for processed file content but instructions require the agent to report specific tool versions and exit codes to maintain transparency.
Capability inventory: The skill has the capability to read files, execute local commands (taplo), and write changes to the filesystem (taplo format).
Sanitization: The skill mitigates risks by explicitly requiring manual diff reviews before applying any fixes and mandating human confirmation for destructive or large-scale changes.
[COMMAND_EXECUTION]: The skill utilizes local shell commands to perform its primary function. It executes taplo --version, taplo lint ., and taplo format to validate and modify TOML files within the defined project scope.

codeguard-toml