The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides several shell scripts (diagnose.sh, check-cors.sh, inspect-cache.sh) and commands in SKILL.md that execute standard development tools including npm, npx, wrangler, curl, git, and lsof. These are used for environment verification, build testing, and remote resource health checks.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and analyze application logs, error messages, and network responses which could potentially contain adversarial instructions.
Ingestion points: scripts/diagnose.sh (command output), scripts/check-cors.sh (HTTP headers), and scripts/inspect-cache.sh (Cloudflare KV data).
Boundary markers: Absent; the skill does not include specific delimiting or instructions to ignore embedded commands in logs.
Capability inventory: The skill uses Bash for shell execution, Write/Edit for file management, and WebFetch for network testing.
Sanitization: None detected for log or error message processing, which is standard for debugging tools.

fullstack-debugger