night-market-diagnostics-toolkit
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
check_pinned_versions.pyscript queries GitHub to verify that tool pins match the latest upstream releases. This is a documented administrative function for maintaining tool currency. - [COMMAND_EXECUTION]: The toolkit executes various local Python and Bash diagnostic scripts within the repository environment. These operations are intended for development-time health checks and repository auditing.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
- Ingestion points: Diagnostic tools read content from
SKILL.mdfiles (viavalidate_budget.py), Markdown files (viacheck-markdown-links.py), and Python source code files (viacheck_docstring_quality.py) within the repository. - Boundary markers: There are no explicit markers or instructions within the scripts to ignore potential agent instructions embedded in the analyzed data.
- Capability inventory: The skill possesses the capability to execute shell commands and scripts based on the results of its analysis of the repo data.
- Sanitization: The provided logic does not demonstrate specific sanitization or escaping of content retrieved from the repository files before processing.
Audit Metadata