The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard development tools including git, npm, and the Cloudflare wrangler CLI to perform deployment operations, rollbacks, and environment management. These actions are consistent with the skill's stated operational purpose.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from production logs and health check responses. \n
Ingestion points: Terminal output from wrangler tail and HTTP responses from curl health checks. \n
Boundary markers: None; the instructions do not provide delimiters or safety warnings to ignore instructions that might be embedded in the log output or API responses. \n
Capability inventory: File system access, network access, and command execution via git, npm, wrangler, and curl. \n
Sanitization: No validation or sanitization is performed on the data retrieved from external logs or API endpoints.
[PROMPT_INJECTION]: The skill contains deceptive metadata, claiming "No network access needed" in the core instructions while providing commands that require active connectivity, such as git push, wrangler rollback, and curl requests to external domains.

paniolo-deployment-operations