skills/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/wrangler/Gen Agent Trust Hub
wrangler
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
wranglercommand-line interface to perform management tasks on Cloudflare services, including deploying workers, managing KV namespaces, interacting with R2 buckets, and executing SQL queries on D1 databases. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external, potentially untrusted sources and has significant capabilities.
- Ingestion points: The skill reads external data via
wrangler kv key get,wrangler r2 object list, andwrangler d1 execute(SKILL.md). - Boundary markers: There are no specific delimiters or instructions to ignore embedded commands when processing the output of these retrieval operations.
- Capability inventory: The skill can execute various CLI commands that modify cloud infrastructure, manage secrets, and perform network-based deployments across all mentioned scripts.
- Sanitization: No sanitization, validation, or escaping of the content retrieved from KV, R2, or D1 is implemented before it is processed by the agent.
Audit Metadata