triage
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs subagents to read and verify findings based on untrusted external artifacts.
- Ingestion points: Findings (id and claim) and artifact paths provided by the caller are processed directly (SKILL.md).
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions within the findings or artifacts.
- Capability inventory: Subagents are tasked with reading artifacts and judging findings, which involves processing potentially malicious content (SKILL.md).
- Sanitization: There is no evidence of sanitization or validation of the input data before it is passed to subagents.
Audit Metadata