architect
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a prompt template in
references/runner-prompt.mdthat interpolates external data into the agent's context. - Ingestion points: Untrusted data enters via the
{GROUNDING}and{TASK}placeholders during the 'Sketch' phase. - Boundary markers: The
references/runner-prompt.mdtemplate does not use specific delimiters or instructions to prevent the agent from following instructions embedded within the provided task or grounding data. - Capability inventory: The skill instructions (SKILL.md) allow the agent to modify production code during the 'Implement' phase.
- Sanitization: The provided files do not include mechanisms to sanitize or validate the content of the interpolated variables.
Audit Metadata