codereview-roasted

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No security risks were identified in the skill's markdown instructions.
  • [NO_CODE]: The skill is composed entirely of text-based prompts and contains no scripts or binaries.
  • [PROMPT_INJECTION]: The skill reviews user-provided code, which is a surface for indirect prompt injection.
  • Ingestion points: User-provided code snippets for analysis via the /codereview-roasted command.
  • Boundary markers: None.
  • Capability inventory: None. The skill is restricted to providing text analysis and is explicitly instructed not to modify code.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 07:38 PM