dev4-implement

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interpolates user-provided input ($ARGUMENTS) directly into a shell command: wt switch -c feat/$ARGUMENTS. This creates a risk of shell command injection if the input contains malicious characters such as semicolons, ampersands, or backticks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external files including prd.md and design.md. This represents an indirect prompt injection surface.
  • Ingestion points: The skill reads files from the .llm/$ARGUMENTS/ directory into the agent context (SKILL.md).
  • Boundary markers: No delimiters or explicit warnings to ignore embedded instructions are used when reading these files.
  • Capability inventory: The agent has the capability to execute shell commands for git operations and running tests, as well as the ability to write files to the local filesystem.
  • Sanitization: There is no evidence of validation or sanitization of the content extracted from the PRD or design documents before the agent acts upon them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:37 AM
Security Audit — agent-trust-hub — dev4-implement