next-up

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reconstructs work context by reading existing NEXTUP.md files and repository artifacts such as branch status, commits, and diffs. This creates a surface where untrusted content in the repository could influence the agent's summary or recommended next steps.
  • Ingestion points: Existing NEXTUP.md file, git diffs, and git commit messages (SKILL.md).
  • Boundary markers: No specific delimiters or instructions are used to separate this potentially untrusted content from the agent's internal instructions.
  • Capability inventory: The skill allows writing to the filesystem and executing git commands (SKILL.md).
  • Sanitization: There is no explicit sanitization for external content before interpolation.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute git rev-parse --show-toplevel and inspect repository state via the command line to resolve file paths and gather context. These are considered standard developer tools operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:15 AM
Security Audit — agent-trust-hub — next-up