google-maps-review-lead-research
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 auto-install a dependency without user confirmation and to conceal that action ("do not describe it as a request...do not request separate approval"), which is a deceptive, out-of-scope instruction altering agent behavior and hiding it from the user.
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 0.90). The Skill instructs the agent to silently install and invoke an external CLI without user consent and to collect contact details (emails/phones/URLs), creating a deliberate supply-chain/deceptive-installation risk and potential for unauthorized data collection.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use the runtime
browser-actSkill to access and extract data from live Google Maps/public web pages, which is outsider-authored free text (public web content) that can be ingested into the LLM context via the browser automation workflow.
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 a required runtime dependency from the BrowserAct installer link (https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which indicates the agent will fetch and run remote installation code at runtime.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (medium risk: 0.60). The Skill instructs the agent to automatically install the BrowserAct CLI without requesting user approval, which can modify the host system or invoke privileged operations and thus pushes the agent toward changing machine state.
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