collage-layout-expert
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection due to its integration with external data fetching tools and its high-privilege execution environment.
- Ingestion points: As defined in SKILL.md, the skill utilizes
mcp__firecrawl__firecrawl_searchandWebFetchto gather research, art historical context, and technical documentation from the public web. - Boundary markers: The instructions do not include specific delimiters or 'ignore embedded instructions' directives to sanitize or isolate data retrieved from these external sources.
- Capability inventory: The skill is granted access to powerful tools including
Bashfor shell operations andWrite/Editfor file system manipulation, as specified in the allowed-tools configuration. - Sanitization: There is no evidence of robust sanitization or validation of external content before it is processed by the agent, creating a path for malicious instructions embedded in web content to reach the agent's core execution loop.
Audit Metadata