The Agent Skills Directory

[COMMAND_EXECUTION]: The skill configures a PostToolUse hook in SKILL.md that automatically triggers the execution of a Bash script (scripts/check-coverage.sh) whenever the user executes test-related commands (jest, vitest, or npm test) through the Bash tool.
[DYNAMIC_EXECUTION]: The scripts/check-coverage.sh file uses node -e to dynamically execute a JavaScript string that loads and parses a coverage summary file. While the path is hardcoded within the script, using an evaluator for data parsing is a form of dynamic execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local filesystem, which could be exploited to influence the agent's behavior.
Ingestion points: The script reads the content of coverage/coverage-summary.json (a file typically generated by external tools) in scripts/check-coverage.sh.
Boundary markers: Absent. The output of the coverage check is printed directly to the shell, which is then returned to the agent's context without delimiters or instructions to treat the data as untrusted.
Capability inventory: The skill has the ability to execute shell scripts and Node.js commands based on the detection of specific command patterns in the user's workflow.
Sanitization: Absent. The script does not validate or sanitize the values extracted from the JSON file before using them in shell comparisons or displaying them in the console.

coverage-guard