The Agent Skills Directory

[SAFE]: The skill defines a standard debugging process including reproduction, hypothesis testing, and regression testing. It encourages best practices like TDD and root cause investigation.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it instructs the agent to process external, potentially untrusted data.
Ingestion points: Error messages, stack traces, event logs, and curl responses are read into the agent context (SKILL.md).
Boundary markers: Absent. The instructions do not specify delimiters or instructions to ignore embedded commands in logs.
Capability inventory: The skill suggests using shell commands for test invocations, curl for network requests, and git for bisection (SKILL.md).
Sanitization: Absent. The skill does not mention filtering or escaping the external content before analysis.
Note: This is an inherent part of the debugging process and is considered low risk in this context.

debug