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 gitoutput package from the NPM registry via npx at runtime.
  • [COMMAND_EXECUTION]: Executes shell commands using npx gitoutput with 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 (via npx), Read (file system access), and Write (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
Risk Level
SAFE
Analyzed
Sep 3, 2026, 10:18 AM
Security Audit — agent-trust-hub — codebase-text-report