offensive-ssti
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided input within template strings. This represents a potential indirect prompt injection surface where the agent processes untrusted data as part of its auditing task.
- Ingestion points: User input concatenated into template strings for dynamic rendering (SKILL.md).
- Boundary markers: No specific boundary markers or delimiters are defined in this procedural guide.
- Capability inventory: The skill utilizes static analysis, binary inspection, and runtime verification tools to audit external code (SKILL.md).
- Sanitization: The methodology includes identifying vulnerabilities and providing remediation via logic-less templates and safe rendering practices.
Audit Metadata