bim-qto
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external BIM data (Excel, CSV, JSON) which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The skill instructions specify that it accepts project data and file paths in CSV, Excel, and JSON formats for processing (instructions.md).
- Boundary markers: There are no explicit boundary markers or delimiters defined in the instructions to separate the untrusted data content from the agent's system instructions.
- Capability inventory: The skill possesses the ability to write to the file system using the
to_excelmethod in SKILL.md and is grantedfilesystempermissions in claw.json. - Sanitization: The implementation does not show explicit sanitization or validation of the data content to filter out potentially malicious natural language instructions.
Audit Metadata