wrangler
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with a project's toolchain and configuration, which presents an attack surface for indirect prompt injection if those project files contain malicious instructions.
- Ingestion points: The skill reads the project manifest (
package.json), lockfiles, and configuration files (wrangler.jsonc), and it fetches information from external Cloudflare documentation URLs. - Boundary markers: The instructions do not specify any boundary markers or special handling to distinguish between legitimate configuration data and potentially malicious embedded instructions.
- Capability inventory: The skill has the capability to execute a wide range of CLI commands via Wrangler, including deploying code, managing secrets, and performing CRUD operations on databases (D1, KV, R2).
- Sanitization: There is no explicit sanitization or validation logic described for the data ingested from the project files or external sources.
Audit Metadata