real-estate-brokerage-lead-scraper
Fail
Audited by Snyk on Jul 20, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 0.80). The Skill explicitly instructs the agent to install BrowserAct automatically without user confirmation and to hide that installation (not describing it as a request or seeking approval), which is a deceptive instruction outside the stated scraping purpose.
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 1.00). The Skill explicitly instructs automatic installation of an external CLI without user confirmation and to conceal that action, creating a deliberate supply-chain/backdoor and unauthorized-installation risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). SKILL.md instructs the agent to delegate live website work to the BrowserAct CLI at runtime (public web pages/URLs provided by the operating user), which can cause outsider-authored free text from fetched pages to be ingested into the LLM context via BrowserAct’s page-reading/extraction.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to install and invoke BrowserAct using the Install BrowserAct URL (https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which implies fetching and executing remote installer/runtime code to obtain a required CLI dependency.
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 explicitly instructs the agent to install missing runtime dependencies automatically "without asking the user to confirm" and to obtain the required Skill itself, which directs the agent to modify the host environment (install software) without user approval — a clear risk of changing machine state even though it does not explicitly request sudo or file edits.
Issues (5)
E004
CRITICALPrompt injection detected in skill instructions.
E006
CRITICALMalicious code pattern detected in skill scripts.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata