decision-analysis-under-uncertainty
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
$ARGUMENTSplaceholder inSKILL.mdto ingest user context, which creates an indirect prompt injection surface where external data could potentially influence agent behavior. - Ingestion points:
SKILL.md(via$ARGUMENTS). - Boundary markers: Absent (user input is interpolated directly without explicit delimiters or instructions to disregard embedded commands).
- Capability inventory: The skill is composed of static documentation and templates with no associated scripts, shell execution, or network capabilities.
- Sanitization: Absent.
Audit Metadata