The Agent Skills Directory

[PROMPT_INJECTION]: The skill's instructions focus on technical guidance for the FlowR framework and do not contain any attempts to override or bypass AI safety constraints.
[COMMAND_EXECUTION]: The skill invokes a local Python script resolve.py to analyze the project environment. Additionally, test_resolve.py uses subprocess.run() for unit testing. These executions are restricted to local scripts and do not utilize a shell, mitigating command injection risks.
[DATA_EXFILTRATION]: No network-enabled tools or sensitive file access patterns were observed. The skill only interacts with local project manifests like pubspec.yaml.
[REMOTE_CODE_EXECUTION]: The skill uses local scripts for setup and validation. It does not download or execute code from remote sources.

flowr-usage