materialcraft
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to discover and execute local binaries (
materialcraftandmaterialcraft-cli) using system utilities such ascommand -v,where, andmdfind. These commands are used to establish a connection to the tool's automation interface. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external material graph files (
.sbs,.mcmat) which contain user-controllable text fields like comments, node labels, and graph descriptions. These fields could be leveraged to provide malicious instructions to the agent during inspection. - Ingestion points: Data returned by the
session.inspectandlibrary.listmethods, as well as file contents read viapackage.open(SKILL.md and references/control-protocol.md). - Boundary markers: The documentation does not specify explicit delimiters or warnings to ignore instructions embedded within graph metadata.
- Capability inventory: The skill possesses the ability to read and write files via
package.saveandoutputs.export, and to execute various engine commands viacommand.run. - Sanitization: No specific sanitization or filtering logic is described for the text fields extracted from the material graphs.
Audit Metadata