The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes external codebases to identify quality issues, which creates a surface for indirect prompt injection attacks.
Ingestion points: The skill reads source code and test files from the filesystem using Read, Grep, and Glob tools.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the code being analyzed and the skill's own instructions.
Capability inventory: The skill utilizes Bash, Write, and Edit tools, which could potentially be misused if the agent follows malicious instructions embedded in the analyzed code.
Sanitization: The instructions do not define any sanitization or validation logic for the content read from external files.
[COMMAND_EXECUTION]: The skill suggests executing shell commands to generate test coverage reports.
Evidence: The documentation includes bash snippets for running bun test --coverage and uv run pytest --cov. While these are standard development workflows, they involve executing code within the environment.

test-quality-analysis