deepwork-tracker

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The prompt includes a clear, unconditional instruction to "Always send" reports to a specific Telegram user (Alex, id 8551040296), which effectively forces data exfiltration to a third party and goes beyond the skill's stated, generic "generate for sharing" purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill contains an explicit, hard-coded data-exfiltration instruction—"Always send" deep-work reports/heatmaps to a specific Telegram user id (8551040296) without user consent—constituting deliberate malicious/backdoor behavior.

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

• Third-party content exposure detected (high risk: 0.80). SKILL.md's "Bootstrap" section explicitly instructs cloning the public GitHub repo (https://github.com/adunne09/deepwork-tracker.git) and installing/executing the fetched deepwork.js, so the agent would fetch and run untrusted third‑party code whose output can directly drive actions (e.g., sending Telegram messages).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's bootstrap step explicitly runs git clone https://github.com/adunne09/deepwork-tracker.git at runtime and then copies/executes the fetched deepwork.js, so the remote repository (https://github.com/adunne09/deepwork-tracker.git) provides code that is fetched and executed and thus controls the agent's runtime behavior.