The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes shell commands to perform its core functions, including running test suites (npm test, pytest, go test, cargo test) and querying git history (git diff). These operations are scoped to standard development workflows but involve direct shell execution.
[DYNAMIC_EXECUTION]: The skill identifies public interfaces in source code to generate new test files and then immediately executes these scripts to verify their success. This involves runtime generation and execution of code based on the project's existing codebase.
[INDIRECT_PROMPT_INJECTION]: The skill reads source code, test files, and configuration files (e.g., package.json, pyproject.toml) from the local directory to inform its generation logic. Maliciously crafted content within these files could potentially influence the agent's behavior during the analysis or generation phase.
Ingestion points: File content is read from the local repository in SKILL.md (specifically in step_1_detect_framework and generate_tests).
Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions that might be embedded within the ingested code or comments.
Capability inventory: The skill has the ability to read/write files and execute shell commands via detected test runners.
Sanitization: There is no explicit sanitization or validation of the content retrieved from the project files before it is used to influence agent output.

test