show-system-prompt

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly directs capturing and printing raw system prompts and API bodies (via OTEL dumps, mitmproxy, binary inspection), which can contain API keys, tokens, environment secrets, or other sensitive values, so it requires handling and likely outputting secrets verbatim.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly runs "npx --yes tweakcc unpack ..." which fetches and executes remote code from the npm/tweakcc package (e.g., https://www.npmjs.com/package/tweakcc or the registry at https://registry.npmjs.org/tweakcc) during runtime, so it is a runtime external dependency that executes remote code.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs using mitmproxy and installing a proxy CA (which alters system trust), and even includes a sudo command to delete a certificate from the system keychain—i.e., it directs privileged, security-sensitive modifications of the machine state.