game-ui-asset-pipeline
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts
scripts/build_sprite_atlas.pyandscripts/export_engine_manifest.pyusing a shell environment. These commands incorporate a<project-id>variable which, if not properly sanitized, could be a vector for command injection. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from YAML contract files which could potentially contain malicious instructions meant to influence the agent's behavior during the asset processing workflow.
- Ingestion points: Reads data from
contracts/atlas-contract.yamlandcontracts/export-contract.yamlin the skill body. - Boundary markers: None identified; there are no instructions to ignore embedded commands within the processed YAML files.
- Capability inventory: The skill has the ability to execute shell commands and run Python scripts (
python3). - Sanitization: No explicit sanitization or validation of the YAML content or the
<project-id>parameter is mentioned in the instructions.
Audit Metadata