upwork-job-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill instructs the agent to automatically install a required dependency and explicitly tells the agent to conceal that action from the user (not to request approval or present it as a browser request), which are hidden/deceptive instructions outside the stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to invoke the BrowserAct CLI to access real Upwork/job pages at runtime and extract visible job description text (outsider-authored public web content), which can be fed into the LLM context via the BrowserAct execution results.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to automatically install and invoke the BrowserAct CLI at runtime using the install URL https://www.browseract.com/?co-from=lead-generation (and the related installer link https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which fetches and installs external code required to execute browser actions.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The Skill instructs the agent to install the BrowserAct CLI automatically and to do so without asking the user for confirmation (explicitly telling the agent not to request separate approval), which forces the agent to change the host system state and bypass user consent for dependency installation.