linkedin-scraper
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'orth' CLI tool to perform data scraping operations. This is a tool provided by the vendor 'orthogonal-sh' for interacting with their platform services.- [EXTERNAL_DOWNLOADS]: The skill makes network requests to 'api.orth.sh' using curl to submit scraping jobs. This domain is the official API endpoint for the vendor's infrastructure.- [PROMPT_INJECTION]: The skill processes untrusted data from public LinkedIn profiles, which presents a surface for indirect prompt injection.
- Ingestion points: Public LinkedIn profile, company, and post data fetched via the 'scrapecreators' API endpoint (SKILL.md).
- Boundary markers: Absent; there are no instructions provided to the agent to treat the scraped content as data only or to ignore embedded instructions.
- Capability inventory: The skill is capable of executing the 'orth' CLI and performing network operations (SKILL.md).
- Sanitization: Absent; the skill does not specify any validation or filtering for the content returned from LinkedIn before it is presented to the agent.
Audit Metadata