cloudflare-workers-publish

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: Accesses the sensitive local file path ~/.claude/.secrets/op-service-account-token. This file contains the 1Password service account token required for the skill to retrieve Cloudflare credentials. This is a documented requirement for the skill's functionality.
  • [COMMAND_EXECUTION]: Executes the npx wrangler command to interact with the Cloudflare Workers API. Cloudflare is a well-known service provider.
  • [EXTERNAL_DOWNLOADS]: Fetches and runs the Cloudflare wrangler CLI via npx. This is a trusted tool from a well-known organization.
  • [REMOTE_CODE_EXECUTION]: Executes the bundled bash script scripts/publish_static.sh which manages the deployment workflow and invokes external tools.
  • [PROMPT_INJECTION]: Susceptible to indirect prompt injection (Category 8) because the scripts/publish_static.sh script ingests local file paths and interpolates them into a generated index.html without sanitization. Evidence: 1. Ingestion points: Local filesystem search via find command in scripts/publish_static.sh. 2. Boundary markers: None. 3. Capability inventory: Public network deployment via npx wrangler deploy. 4. Sanitization: None; filenames are placed directly into HTML tags.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 05:28 PM