affordable-housing
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted codebase files and project configuration data without utilizing boundary markers or sanitization, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads local project files, configuration files, and database schemas during the System Architecture Discovery and Audit phases (SKILL.md).
- Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present around the ingested content or the $ARGUMENTS variable.
- Capability inventory: The skill performs file system write operations to the
docs/directory and the agent's internal~/.claude/projects/directory. - Sanitization: There is no evidence of sanitization or validation of the ingested file content before it is added to the agent's context.
Audit Metadata