constructor
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and acts upon untrusted data from a project brief.
- Ingestion points: The skill reads project brief content from
ideator-output/project-brief.mdor a user-specified path in Step 0. - Boundary markers: There are no delimiters or explicit instructions to the AI agent to disregard potential instructions hidden within the ingested brief content.
- Capability inventory: The skill is granted broad capabilities via
read,write,edit, andexectools, which could be exploited if an injection occurs. - Sanitization: The skill performs no sanitization, escaping, or validation of the brief's content before using it to influence architectural decisions.
Audit Metadata