The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes lint-red.sh, a local shell script designed to verify TDD commit protocols by inspecting git history and staged changes using git diff and git log. This is standard behavior for a development-focused linter.- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes untrusted data from the repository's git logs and file contents.
Ingestion points: lint-red.sh reads git commit messages and file diffs.
Boundary markers: None explicitly defined for the ingested data.
Capability inventory: Includes shell execution for linting purposes.
Sanitization: Uses regex patterns for validation but lacks formal sanitization of the external content before it enters the agent's context. The risk is considered minimal as the script primarily performs read-only validation.

tdd