project-impact
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow includes an instruction to run a local script
scripts/project_status.pyto support hash-based change detection. This is a standard maintenance operation within the context of the project-impact tool. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it is designed to read and process external configuration and state files.
- Ingestion points:
00_project/dependencies.jsonand artifact state files. - Boundary markers: The instructions do not specify explicit delimiters for the ingested data.
- Capability inventory: The skill utilizes local script execution (
scripts/project_status.py). - Sanitization: No specific sanitization or validation steps for the input files are mentioned in the prompt instructions.
Audit Metadata