linkedin-job-scraper
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external LinkedIn job listings, which introduces a surface for indirect prompt injection attacks.
- Ingestion points: The script
jobspy_scraper.pyfetches job titles and full descriptions from LinkedIn. - Boundary markers: There are no explicit delimiters or warnings provided to the agent to distinguish scraped content from its primary instructions.
- Capability inventory: The skill possesses network access for scraping and file-write capabilities for saving results to the
.tmp/directory. - Sanitization: No sanitization is performed on the scraped job description text before it is returned to the agent context.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
python-jobspypackage from a public registry. This is an expected dependency for the skill's stated purpose.
Audit Metadata