The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs widely-used testing libraries including hypothesis, pytest, fast-check, and QuickCheck using official package managers (pip, npm, cabal) from their respective public registries.
[COMMAND_EXECUTION]: The skill uses Bash to perform environment discovery (checking for configuration files like package.json or pytest.ini) and to execute package installation commands.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data:
Ingestion points: Reads source code and configuration files via the Read and Glob tools to identify testing requirements and function properties.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions hidden in code comments or strings within the files it reads.
Capability inventory: The agent has access to Bash (command execution) and Write (file creation) tools which could be targeted by an injection attack.
Sanitization: No explicit sanitization or filtering is performed on the content ingested from the project files before it influences the generated output or shell commands.

property-based-test-generator