The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and act on external data provided by the user, creating a surface for indirect prompt injection. Ingestion points: The skill requests symptom details, reproduction steps, and context from the user. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the prompt structure. Capability inventory: The skill directs the agent to reproduce, isolate, and fix bugs, which involves the use of shell and filesystem tools like git. Sanitization: The skill does not define any validation or sanitization logic for the provided reproduction steps.
[NO_CODE]: The skill consists entirely of instructional markdown and does not include any scripts, binaries, or automated tool configurations.

bug-diagnosis