docker-compose-creator
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it is designed to ingest and process user requests and local repository content to generate configurations using powerful tools.
- Ingestion points: Untrusted data enters the agent context through user requests triggered by keywords like "docker" and through existing files in the development environment via the Read tool.
- Boundary markers: There are no instructions or delimiters defined to help the agent distinguish between data to be processed and instructions that might be embedded within that data.
- Capability inventory: The skill environment permits the use of Bash(cmd:*), Write, Edit, and Read tools (as defined in the frontmatter of SKILL.md), which could be leveraged if the agent is misled by malicious content.
- Sanitization: The skill does not define any sanitization, filtering, or validation logic for the external content it processes.
Audit Metadata