The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides procedures for the agent to execute shell commands such as grep, awk, and tail to analyze local log files (logs/calling-service.log, logs/error.log). This usage is strictly diagnostic and aligns with the skill's primary purpose.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and analyze external data including conversation transcripts and system logs.
Ingestion points: Conversation transcripts retrieved via mcp__elevenlabs__elevenlabs_get_conversation and local log files.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the diagnostic templates.
Capability inventory: The skill utilizes Bash, Write, Edit, Read, and Grep tools.
Sanitization: The provided scripts do not perform explicit sanitization of transcript content before processing.

agent-debugging