astrofy-cloudflare-deploy
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and interpret configuration files such as
package.json,cloudflare.config.ts, andwrangler.jsonc, which constitutes an ingestion point for untrusted data if the project files are malicious.\n - Ingestion points: Defined in
SKILL.mdandtechnical.mdas reading project configurations, scripts, and build output metadata.\n - Boundary markers: The instructions do not define specific delimiters to isolate file content from the agent's instructions, nor do they provide explicit warnings to the agent to ignore embedded instructions in those files.\n
- Capability inventory: The skill utilizes shell command execution via the
cf,wrangler, andastrofyCLI tools, which include network deployment capabilities.\n - Sanitization: The skill relies on manual user review and the use of the
--dry-runflag for safety, but it does not perform automated sanitization of the data ingested from the configuration files.\n- [COMMAND_EXECUTION]: The skill involves the execution of build and deployment commands through the command line. This is expected behavior for a deployment-focused skill.\n- [EXTERNAL_DOWNLOADS]: The skill references official technical documentation from Cloudflare, which is a well-known and trusted service provider.
Audit Metadata