didit-transaction-monitoring
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests transaction data and subject names provided as command-line arguments, which are then transmitted to the monitoring API. This represents a potential surface for indirect prompt injection if untrusted data is processed without sanitization, though the risk is inherent to the skill's primary purpose.
- Ingestion points:
submit_transaction.pyaccepts user-supplied strings for--subject-name,--counterparty-name, and--vendor-data. - Boundary markers: None explicitly used in the prompt interpolation within the markdown instructions.
- Capability inventory: The skill uses the
requestslibrary to perform network operations (requests.post) to Didit's API endpoints. - Sanitization: No explicit sanitization or filtering of user-provided strings is performed in
submit_transaction.pybefore they are included in the JSON payload sent to the API.
Audit Metadata