portfolio-sync
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes untrusted data from external prediction markets and presents it directly to the agent's context.
- Ingestion points: Data is ingested via
service.getPositionsByPlatformandservice.getSummaryinindex.ts. - Boundary markers: Absent. The output is formatted as a plain markdown list without delimiters or instructions to the LLM to ignore embedded commands.
- Capability inventory: The skill primarily performs string formatting; however, the agent's overall capability set (not fully visible here) could be leveraged if the agent obeys instructions hidden in market titles.
- Sanitization: The
marketQuestionandmarketIdfields are used directly in the output string without escaping or validation.
Audit Metadata