align-architecture
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill's primary function involves ingesting and analyzing untrusted data from the project's source code and architecture documentation (ADRs). This allows for potential injection if those files contain malicious instructions meant to subvert the agent's reporting logic.
- Ingestion points: Architecture documentation paths (e.g., docs/architecture/, docs/design-decisions/) and the project codebase as defined in SKILL.md.
- Boundary markers: Absent; the instructions do not implement specific delimiters or 'ignore' instructions for the ingested content.
- Capability inventory: The skill reads files for analysis and writes the final Architecture Compliance Report to the local file system (docs/calibration/architecture-compliance.md).
- Sanitization: There is no evidence of content sanitization or validation before the ingested data is processed by the agent.
Audit Metadata