14-ai-integration
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied business data, creating a potential attack surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context via the 'Generation Process' in
SKILL.md, which asks the user for industry details, tech stack, pain points, and budget constraints. - Boundary markers: The instructions lack explicit delimiters (e.g., XML tags or triple quotes) or warnings to the agent to ignore instructions embedded within the user-supplied business data.
- Capability inventory: The skill's capability is restricted by its contract to 'read-only analysis and drafting,' minimizing the impact of potential injections as no file-write, network, or command-execution operations are authorized.
- Sanitization: There are no specific instructions for filtering or sanitizing the input data before it is interpolated into the planning workflow.
Audit Metadata