The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the espeak-ng system command to generate speech. The implementation in espeak_skill.py uses subprocess.Popen with a command list rather than a raw shell string, preventing shell injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing the necessary espeak-ng dependency, including a link to the official releases on GitHub. This reference targets a well-known open-source project and is used for environment setup.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for speech generation. It successfully mitigates potential injection risks through the following measures: 1. Ingestion points: Untrusted data enters via sys.argv[1] in espeak_skill.py. 2. Boundary markers: Not explicitly used, but the input is isolated within a command argument list. 3. Capability inventory: Uses subprocess.Popen to invoke the local espeak-ng binary. 4. Sanitization: Applies a strict regular expression filter that removes all special characters, ensuring only alphanumeric characters and spaces are processed.

espeak-ng