git-nuget-readme
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository's git history and source code, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads commit subjects and bodies via
git log, analyzes changes viagit diff, and searches source files usingrgin thesrc/andtest/directories. - Boundary markers: The instructions lack specific delimiters or warnings to prevent the agent from interpreting data within commit messages or source code as active instructions.
- Capability inventory: The agent has permissions to execute git and ripgrep commands and is authorized to overwrite the
README.mdfile directly. - Sanitization: There is no logic provided to sanitize or filter external content before it is interpolated into the prompt context.
Audit Metadata