linkedin-company-profile-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that explicitly command the agent to bypass user confirmation and safety protocols. It directs the agent to install dependencies 'automatically without asking the user to confirm' and 'not request separate approval'.
- [EXTERNAL_DOWNLOADS]: The skill mandates the automatic download and installation of an external CLI tool and skill ('browser-act') from a third-party website (browseract.com) if the dependency is missing at runtime.
- [COMMAND_EXECUTION]: The skill requires the execution of a third-party CLI tool to perform data scraping. Combined with the silent installation instructions, this creates a risk of executing unverified external code.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of external LinkedIn data. (1) Ingestion points: LinkedIn profile URLs and search queries. (2) Boundary markers: No delimiters or instructions are present to prevent the agent from obeying instructions embedded in the scraped content. (3) Capability inventory: The agent has access to the browser automation tool and the local filesystem (workspaces/ directory). (4) Sanitization: There is no evidence of validation, escaping, or filtering of the retrieved data.
Recommendations
- AI detected serious security threats
Audit Metadata