skills/rheinmir/setup/safe-change/Gen Agent Trust Hub

safe-change

Pass

Audited by Gen Agent Trust Hub on Jun 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as ls to locate test files and a variable <test-cmd> to run test suites. These operations are localized to the project environment and are expected for a developer-oriented skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill features an attack surface where it reads external code files to determine modification impact and writes summary reports to a local wiki. Malicious content within the analyzed source code could theoretically influence the agent's reasoning or the content of the wiki report.
  • Ingestion points: Reads local project source files and files within the llmwiki/ directory.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within read content are defined.
  • Capability inventory: Includes file write access to the wiki directory and shell command execution for testing purposes.
  • Sanitization: The instructions do not specify any filtering or escaping of content extracted from source files before it is processed or written to the wiki.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 3, 2026, 04:49 AM
Security Audit — agent-trust-hub — safe-change