setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill prompt instructs the agent to ask the user to paste API keys and tokens in plain text, and it embeds those tokens directly into command-line headers and requests (e.g., curl calls with Bearer tokens and custom headers), creating a credential exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required setup workflow configures communication channels such as email, Telegram, WhatsApp, Slack, and Discord, which ingest messages and outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs cloning an unofficial repository from GitHub (https://github.com/Lifecycle-Innovations-Limited/wacli, https://github.com/steipete/gogcli, https://github.com/DopplerHQ/scoop-doppler.git, https://github.com/gsd-build/get-shit-done, and https://github.com/maorfr/slack-token-extractor) during setup/runtime, which constitutes a common/reputable unofficial operational dependency.