design-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and follow instructions from a local configuration file (
.design-engineer/system.md). This allows external data to influence the agent's logic and design decisions. - Ingestion points: Reads
.design-engineer/system.mdfrom the project root directory. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential injection attempts within the project-specific system file.
- Capability inventory: The agent is authorized to read local project files (e.g.,
package.json,.git,src/) and write a new configuration file (.design-engineer/system.md) to the file system. - Sanitization: There is no mention of sanitizing or validating the content retrieved from the configuration file before incorporating it into the agent's working context.
Audit Metadata