mpp-service-discovery
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process data from external domains (
paymentauth.org,mpp.dev) and perform web searches to find implementation examples. This untrusted content is used to guide the agent's code implementation, creating a surface where malicious instructions embedded in external resources could influence the agent's behavior. - Ingestion points:
https://paymentauth.org/,https://mpp.dev/overview, and web search result snippets for MPP service discovery. - Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore instructions within the fetched data.
- Capability inventory: The skill has access to sensitive tools including
Write,Edit, andBash, which could be abused if the agent obeys malicious instructions from external sources. - Sanitization: No sanitization or validation of the external content is performed before it is processed by the agent.
- [DATA_EXFILTRATION]: The skill performs network operations to non-whitelisted external domains (
paymentauth.org,mpp.dev) usingWebFetchto retrieve protocol specifications and documentation.
Audit Metadata