agent-cloudflare
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Cloudflare API endpoints which could potentially contain malicious payloads designed to influence agent behavior.
- Ingestion points: Data retrieved from Cloudflare APIs via the
agent-cloudflareCLI, specifically resource listings, DNS record contents, and Worker script details inreferences/commands.mdandreferences/scenarios.md. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the tool's output.
- Capability inventory: The skill utilizes the
Bashtool for both information retrieval and resource mutation (e.g., DNS creation, cache purging), alongside file system tools likeRead,Grep, andGlob. - Sanitization: No specific sanitization or validation of the content within API responses is described, although the tool itself is designed to be secret-safe for credentials.
Audit Metadata