The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and contains no executable code, scripts, or automated tool configurations.
[SAFE]: Environment variable instructions correctly advise users to avoid committing secrets to version control, recommending the use of .gitignore and hosting platform dashboards for sensitive keys.
[SAFE]: References to hosting platforms (Vercel, Railway, Netlify, Supabase, etc.) and domain registrars (Cloudflare, Namecheap) target well-known, established services.
[INDIRECT_PROMPT_INJECTION]: The skill provides a template prompt for debugging where users are encouraged to paste application logs into the AI context. This represents an attack surface where malicious content within logs could attempt to influence the agent's behavior.
Ingestion points: User-supplied error logs pasted into the chat prompt (SKILL.md).
Boundary markers: None present in the suggested prompt template.
Capability inventory: None; the skill is informational and does not define tools or scripts.
Sanitization: No sanitization or validation of the log content is suggested.

deploy