skills/wallabyjs/skills/wallaby/Gen Agent Trust Hub

wallaby

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and act upon data from external repository files that could be influenced by a malicious actor. Specifically, the agent is told to read Software Requirements Specifications (SRS), product documentation, and architecture decisions to establish a basis for changing tests or source code.\n
  • Ingestion points: Untrusted repository documentation (SRS, API contracts), source code, and Wallaby reports as described in references/improve.md.\n
  • Boundary markers: There are no instructions for the agent to use delimiters or to disregard instructions that might be embedded within these external documents.\n
  • Capability inventory: The agent is authorized to write to the file system (modifying tests and source files) and execute CLI commands (analyze, inspect, lint, tsc).\n
  • Sanitization: The instructions do not define any sanitization or validation steps for the content processed from external files.\n- [COMMAND_EXECUTION]: The skill's workflow involves executing shell commands to perform analysis and verification. This includes Wallaby-specific tools (analyze, inspect) and standard project verification tools (e.g., lint, tsc). While these are legitimate tools for a testing skill, they provide an execution capability that operates on the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 06:25 AM
Security Audit — agent-trust-hub — wallaby