The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process and diagnose error messages and tracebacks provided by users or tools, which acts as an ingestion point for untrusted data that could contain malicious prompts.
Ingestion points: The skill instructions prompt the agent to "Trigger on any error message that mentions besser in the traceback" (SKILL.md).
Boundary markers: The skill does not provide explicit delimiters or instructions for the agent to differentiate between the technical traceback content and potentially malicious embedded text.
Capability inventory: The skill has access to shell commands (via suggested fixes) and environment inspection capabilities.
Sanitization: No sanitization or validation logic is defined for the input tracebacks.
[COMMAND_EXECUTION]: The skill provides numerous shell commands for environment management and diagnostics, which is standard for developer tools but requires execution oversight.
Evidence: Suggested commands include pip install, docker stop <container_id>, lsof -i :8000, and apt install libpq-dev to resolve dependencies and port conflicts.

besser-troubleshooting