boring-remix

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it transforms untrusted user content (social posts, emails, blogs) into new versions.
  • Ingestion points: User-provided content enters the agent context via the chat interface for transformation as described in SKILL.md.
  • Boundary markers: No delimiters or 'ignore embedded instructions' warnings are present to isolate the user's content from the system's instructions.
  • Capability inventory: The skill reads local markdown files including world-code/voice.md, world-code/conversation.md, and references/boring-ref-content-themes-to-posts.md. No network operations, shell execution, or file write capabilities are present.
  • Sanitization: There is no evidence of input validation or sanitization to filter out malicious instructions from the content being remixed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 09:28 PM