agent-config-audit

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes user-controlled configuration files that define agent behavior. Malicious instructions embedded in these files could potentially influence the agent during the auditing or 'fix' workflow.
  • Ingestion points: The skill reads multiple workspace files including CLAUDE.md, CODEX.md, AGENTS.md, .cursorrules, and .claude/settings.json.
  • Boundary markers: There are no explicit delimiters or instructions provided in the workflow to distinguish file content from the agent's core instructions.
  • Capability inventory: The skill is granted Write, Edit, and Bash permissions, allowing it to modify the very files that govern agent behavior.
  • Sanitization: No sanitization or validation of the file content is performed before processing or rewriting.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 12:11 AM