code-simplifier-agent

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the source code it processes. An attacker could place instructions inside comments or strings in the target code to influence the agent's behavior. Ingestion points: The agent reads local files using find and grep (SKILL.md). Boundary markers: Absent. Capability inventory: The agent can execute shell commands (npm, git, find, grep) and modify file contents (SKILL.md). Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill uses various shell commands to perform its workflow. Evidence: The Process Workflow section includes find, grep, npm test, npm run typecheck, npm run lint, and git diff.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 11:08 AM
Security Audit — agent-trust-hub — code-simplifier-agent