rocketlist-job-search

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's helper script (scripts/rocketlist.py) downloads job and company datasets in compressed JSONL format from the rocketlist-ai/startup-jobs repository on GitHub. These downloads are performed from a well-known service and are necessary for the skill's primary function.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes third-party data from external job postings, which constitutes an attack surface for indirect prompt injection. To mitigate this risk, the SKILL.md file includes an explicit 'Untrusted-data boundary' instruction, directing the agent to treat all retrieved fields as data rather than instructions and to ignore any embedded commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 12:08 AM