model-adaptation
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external prompt data and documentation.
- Ingestion points: The skill ingests user-supplied 'Universal prompt brief' and 'Current docs' as defined in the required inputs of
SKILL.md. - Boundary markers: There are no specific delimiters or ignore-embedded-instruction markers defined in the workflow to isolate these inputs.
- Capability inventory: The skill's operations are confined to text-based analysis and transformation, with no access to the file system, network, or command execution.
- Sanitization: No explicit sanitization or escaping techniques for user-provided prompt content are described in the instructions.
Audit Metadata