instagram-profile-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions require the agent to download and install the 'BrowserAct' CLI and skill from an external URL (browseract.com) if they are not already present in the environment.
- [REMOTE_CODE_EXECUTION]: The instructions explicitly command the agent to bypass user consent by performing the installation "automatically without asking the user to confirm." This facilitates the silent execution of third-party code downloaded from a remote source.
- [PROMPT_INJECTION]: The skill is designed to ingest and process content from public Instagram profiles (bios, names, posts), which serves as an untrusted external data source for indirect prompt injection.
- Ingestion points: Instagram profile pages and account data processed via the browser-act tool.
- Boundary markers: The instructions do not provide delimiters or warnings to treat ingested data as untrusted text.
- Capability inventory: The skill utilizes the browser-act tool to execute browser workflows and interactive tasks.
- Sanitization: There are no instructions for sanitizing or escaping the scraped content before the agent processes it.
Recommendations
- AI detected serious security threats
Audit Metadata