audit-prep-assistant

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill explicitly instructs the agent to execute shell commands for static analysis, including slither . --exclude-dependencies, dylint --all, and golangci-lint run. It further states that it will 'Execute appropriate tools for your platform' and 'Run coverage tools'.
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to its design of processing untrusted data with high-privilege capabilities.
  • Ingestion points: The agent reads the user's entire codebase, including source files and potentially third-party dependencies.
  • Boundary markers: There are no instructions for the agent to use delimiters or ignore instructions embedded within the code comments or documentation it processes.
  • Capability inventory: The agent is authorized to execute shell commands, modify files (to 'fix easy issues' or 'remove dead code'), and generate complex documentation.
  • Sanitization: No sanitization or validation of the codebase content is performed before the agent processes it or uses it to inform its actions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 10:19 PM
Security Audit — agent-trust-hub — audit-prep-assistant