hand-drawn-infographic-creator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is designed to ingest untrusted data from the web to influence its output.
  • Ingestion points: The skill instructions in SKILL.md direct the agent to use the mcp__firecrawl__* tool to search for and read content from external websites to gather 'compositional inspiration'.
  • Boundary markers: The prompt construction logic lacks clear delimiters or instructions to treat external web content as untrusted data, increasing the risk that instructions embedded in a poisoned webpage could be executed by the agent.
  • Capability inventory: The agent has access to powerful tools, including file system access (Read, Write, Edit) and specialized AI image generation tools (mcp__stability-ai__*, mcp__ideogram__*).
  • Sanitization: The skill does not implement sanitization or validation of the data retrieved from the web before using it to build prompts for the image generation tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 01:22 PM