job-scraper
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlcommands to interact with the Apify API to trigger and retrieve results from job scraping tasks. This is a standard method for API integration within this environment. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its core function of ingesting third-party job listings.
- Ingestion points: External job descriptions, titles, and company metadata are retrieved from LinkedIn and Indeed via Apify actors (automation-lab/linkedin-jobs-scraper and borderline/indeed-scraper).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when presenting scraped content to the agent.
- Capability inventory: The skill performs network operations via
curland is capable of generating and writing CSV files to the local system. - Sanitization: There is no mention of sanitizing or escaping the text of job descriptions before they are processed by the agent or exported to files.
Audit Metadata