pipeline-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 is designed to process business signals from external, untrusted sources such as JSON or CSV webhooks, which creates a potential surface for indirect prompt injection.
- Ingestion points: The
run.pyscript reads untrusted content from a file path provided via the--inputcommand-line argument. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between data and embedded instructions within the processed input.
- Capability inventory: The skill has the capability to read any file accessible to the execution environment via
Path(args.input).read_text()and write output to the file system. - Sanitization: The script performs no validation or sanitization on the keys or values of the ingested JSON payload beyond basic parsing.
Audit Metadata