debug-workers-edge
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Cloudflare Workers/Pages logs and request IDs, which could be used to deliver malicious instructions to the agent.
- Ingestion points: Workers/Pages logs and request IDs (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the log data.
- Capability inventory: The skill utilizes powerful tools including wrangler_deploy, execute_command, write_file, and edit_file (SKILL.md).
- Sanitization: No sanitization or verification of the external log content is specified before processing.
Audit Metadata