Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
brightdata-sdkPython package, which is the official SDK provided by the vendor and is used for interacting with the scraper API. - [COMMAND_EXECUTION]: The skill documentation includes various CLI commands using the
bdatatool to trigger scraping pipelines, manage data snapshots, and run local authentication scripts. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources (Instagram profiles, posts, reels, and comments), which may contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Data is retrieved via the Scraper API through the CLI, SDK methods, and MCP tools as described in
SKILL.mdandreferences/sdk.md. - Boundary markers: No specific delimiters or instructions are provided to the agent to treat the scraped content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill allows the agent to execute CLI commands, run Python code using the SDK, and perform file system operations such as saving results to CSV files.
- Sanitization: There is no evidence of content sanitization or filtering of the retrieved social media data before it is processed or displayed to the user.
Audit Metadata