sales-webhook-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured input from external webhooks, which presents a surface for indirect prompt injection.
- Ingestion points: The
run.pyscript ingests data from a file specified by the--inputcommand-line argument. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the ingested webhook data as untrusted or to ignore embedded instructions.
- Capability inventory: The implementation in
run.pyincludes file read (Path.read_text) and file write (Path.write_text) capabilities. - Sanitization: The script lacks logic to sanitize or validate the input JSON/CSV data before processing it or writing it to the output destination.
Audit Metadata