codebase-text-report
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and runs the
gitoutputpackage from the NPM registry vianpxat runtime. - [COMMAND_EXECUTION]: Executes shell commands using
npx gitoutputwith a user-supplied<target>. This creates a surface for command injection if shell metacharacters are not properly handled within the<target>parameter. - [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to instructions embedded in processed codebases (Category 8c).
- Ingestion points: Remote Git repositories or local directories provided as the
<target>argument (Step 1). - Boundary markers: Absent; the instructions do not specify using delimiters or 'ignore instructions' warnings when the agent reads the plain-text chunks (Step 2).
- Capability inventory: The skill environment provides
Bash(vianpx),Read(file system access), andWrite(file system access) tools. - Sanitization: No content filtering or escaping is implemented before the agent processes the chunks to generate the final report (Step 3).
Audit Metadata