riveter
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by ingesting and processing untrusted data from external web pages.
- Ingestion points: The skill fetches external content via the
/v1/scrapeand/v1/runendpoints using user-provided URLs. - Boundary markers: There are no delimiters or instructions provided to the agent to treat scraped content as untrusted data or to disregard instructions contained within that content.
- Capability inventory: The skill utilizes the
orthCLI tool to perform network requests and data processing tasks. - Sanitization: No evidence of content sanitization or instruction filtering for fetched data is present in the skill definition.
Audit Metadata