job-application-operator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external job application forms. This creates an attack surface where a malicious website could attempt to override agent instructions via hidden fields or labels to manipulate the application process or exfiltrate data.
- [DATA_EXPOSURE]: The skill is configured to load sensitive personal information from local files in
~/.config/AgentDesk/, includingpersonal-profile.yamlandfield-answers.yaml. While this is the intended purpose of the skill, it involves handling high-value identity data. - [COMMAND_EXECUTION]: The skill uses browser automation to interact with external web forms, navigate pages, and upload documents based on the content of visited sites.
Audit Metadata