social-graphics

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill is composed exclusively of Markdown documentation and text-based prompt templates. No scripts, binaries, or configuration files were found.
  • PROMPT_INJECTION (SAFE): Analysis of the instructional text found no attempts to bypass safety filters, extract system prompts, or override agent constraints.
  • CREDENTIALS_UNSAFE (SAFE): No sensitive credentials, API keys (including for FAL.ai mentioned in integrations), or private tokens are present.
  • DATA_EXFILTRATION (SAFE): There are no file system access commands or network outbound operations that could be used to exfiltrate data.
  • INDIRECT_PROMPT_INJECTION (SAFE): While the skill defines templates that accept external variables (e.g., [subject], [mood]), it does not possess any capabilities (like file writing or shell execution) that could be exploited via these injection surfaces.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:22 PM