comparejobs
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a well-defined, manual workflow to compare local assessment files. It includes platform-level hardening by setting
disable-model-invocation: true, which restricts the agent's autonomous capabilities while executing this skill. - [DATA_EXPOSURE]: The skill accesses local files (assessment reports and a configuration file). This behavior is consistent with its stated purpose of comparing job applications within a specific workspace. It does not perform any network operations or access sensitive system-level credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external files (
assessment.md) which may contain untrusted content. However, the instructions provide a strict extraction template and focus on specific data fields (scores, categories, strengths), which significantly reduces the risk of the agent being manipulated by instructions embedded within those files.
Audit Metadata