prepare-release-notes

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard Git and filesystem commands (git status, find, sort) to identify pending change files in the packages/ directory. These operations are scoped to the local repository.
  • [SAFE]: The skill invokes project-specific validation and preview scripts via pnpm changes:validate and pnpm changes:preview. These are expected development workflows for the React Router project structure.
  • [PROMPT_INJECTION]: The skill ingests external data from local markdown files, which represents an indirect prompt injection surface.
  • Ingestion points: Reads all content from files located at packages/*/.changes/*.md and scripts/changes/whats-changed.md (SKILL.md).
  • Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore embedded instructions in the processed files.
  • Capability inventory: The agent can execute shell commands (git, find, pnpm) and write to local files (scripts/changes/whats-changed.md).
  • Sanitization: None; the agent is directed to perform text transformations (normalization) directly on the input content.
  • [SAFE]: No network exfiltration, hardcoded credentials, or obfuscated content were detected. All external resources (React Router package structure and scripts) trace back to the vendor's expected infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 10:57 AM
Security Audit — agent-trust-hub — prepare-release-notes