mobile-webhook-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured input (JSON/CSV) from external sources, which creates a potential surface for indirect prompt injection attacks where malicious instructions could be embedded in the data.
- Ingestion points: The
run.pyscript reads payload data from a user-provided file path via the--inputargument. - Boundary markers: The skill uses
json.loadsto structure the data, but lacks explicit prompt delimiters or instructions to the model to ignore embedded commands within the values. - Capability inventory: The skill has local file system read and write capabilities as demonstrated in
run.pyusing thepathlibmodule. - Sanitization: The implementation relies on standard JSON parsing and does not include logic to sanitize or escape natural language instructions that might be present in the business signals.
Audit Metadata