create-branch-not-pushed

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process recent Git commits, which represents an ingestion point for untrusted data if the repository has external contributors. * Ingestion points: Recent Git commit history and metadata. * Boundary markers: Absent from the provided instructions. * Capability inventory: Git branch creation and network operations (pushing to GitHub). * Sanitization: No logic is provided to sanitize or validate commit messages or metadata before processing.
  • [NO_CODE]: The skill package contains no executable scripts, source code, or binary files, consisting solely of a markdown documentation file.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:31 PM
Security Audit — agent-trust-hub — create-branch-not-pushed