collage-layout-expert

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill integrates tools such as Firecrawl and WebFetch, which allow the agent to ingest data from external websites. This capability introduces a vulnerability to indirect prompt injection, where an attacker could place instructions on a webpage to influence the agent's behavior.\n
  • Ingestion points: External data is retrieved through Firecrawl search queries and WebFetch operations as referenced in the skill's tool definitions and implementation guides.\n
  • Boundary markers: The skill does not provide specific instructions or markers to distinguish between the agent's primary instructions and untrusted content fetched from the web.\n
  • Capability inventory: The agent has access to powerful tools, including Bash for command execution, file system Write access, and image generation capabilities.\n
  • Sanitization: There are no mechanisms described for sanitizing or filtering instructions from the external content before it is processed by the agent.\n- [SAFE]: The core algorithmic logic and artistic style guides are based on established mathematical principles and art history, with no signs of obfuscation or direct malicious code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 02:02 PM