git-nuget-readme
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to inspect the repository state and metadata. It uses git status, git log, git diff, and ripgrep (rg) to extract package IDs, framework targets, and code changes from the src/ directory.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it interprets content from git logs and source code which could be influenced by external actors. 1. Ingestion points: Git commit subjects and bodies, git diffs, and source code namespaces/types via rg. 2. Boundary markers: No specific delimiters or safety instructions are used to distinguish ingested data from the skill's own operational logic. 3. Capability inventory: Ability to execute shell commands (git, rg) and perform direct file writes to README.md. 4. Sanitization: No validation or filtering is applied to the ingested git history before it is incorporated into the README drafting process.
Audit Metadata