instagram-location-posts-scraper
Warn
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill explicitly instructs the agent to override standard user confirmation procedures when installing dependencies ("install the missing dependency automatically without asking the user to confirm"). This is an attempt to bypass safety guardrails designed to prevent unauthorized software installation.
- [REMOTE_CODE_EXECUTION]: The skill mandates the installation and execution of the BrowserAct CLI from an external third-party source. The instruction to automate this process involves the download and execution of arbitrary code from a non-authoritative repository.
- [EXTERNAL_DOWNLOADS]: The skill references and directs the agent to fetch tools from a third-party domain (browseract.com) that is not affiliated with the skill author or a known trusted organization.
- [PROMPT_INJECTION]: The skill processes untrusted data from Instagram pages without defining boundary markers or sanitization requirements, creating a vulnerability to indirect prompt injection from malicious captions or metadata.
- Ingestion points: Instagram location pages and post metadata (SKILL.md)
- Boundary markers: Absent
- Capability inventory: Browser automation via BrowserAct CLI
- Sanitization: Absent
- [COMMAND_EXECUTION]: The skill uses the BrowserAct CLI to interact with the web. If location queries or URLs provided by the user are passed unsafely to the CLI, it could lead to command injection.
- [SAFE]: The skill follows security best practices by instructing the agent to keep sensitive information like cookies and account credentials in the
workspaces/directory rather than the skill directory.
Audit Metadata