recurring-charge-detector
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats were identified in this skill. The logic is focused on statistical analysis and data categorization of transaction records.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill processes financial transaction data, but it does so within the agent's local context. There are no instructions or capabilities to exfiltrate this data to external servers or write it to unauthorized local files.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted transaction descriptions, it lacks the dangerous capabilities (network access, command execution, or dynamic evaluation) that would make it vulnerable to exploitation via indirect injection. It treats input fields as data for clustering rather than instructions.
Audit Metadata