dnd-campaign-starter

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No attempts to override agent instructions or bypass safety guardrails were detected. The instructions are focused exclusively on content generation for tabletop games.
  • [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file paths, or network operations (e.g., curl, wget) were found. The skill operates entirely within the chat context.
  • [OBFUSCATION]: No Base64, zero-width characters, homoglyphs, or other encoding techniques were identified in the markdown content.
  • [REMOTE_CODE_EXECUTION]: The skill does not define any dependencies, package installations, or remote script execution patterns.
  • [DYNAMIC_EXECUTION]: No use of eval(), exec(), or runtime code generation. The skill generates natural language text outputs only.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided inputs (such as game tone and player preferences), it lacks access to tools or APIs that could be exploited via malicious data ingestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:28 AM
Security Audit — agent-trust-hub — dnd-campaign-starter