skills/lawve-ai/awesome-legal-skills/eu-ai-act-high-risk-implementation-readiness/Gen Agent Trust Hub
eu-ai-act-high-risk-implementation-readiness
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill package is composed entirely of Markdown documentation, instructional guidance, and reporting templates. No executable code, scripts (.py, .js, .sh), or binary files were found. All activities occur within the AI's conversational context.
- [PROMPT_INJECTION]: The skill ingests untrusted user descriptions of AI systems, creating a surface for indirect prompt injection. This surface is evaluated as safe because the skill does not utilize any tools or capabilities (such as shell access, file system writes, or network requests) that could be abused via malicious input.
- Ingestion points: User input provided during the initial scoping and intake questions (SKILL.md).
- Boundary markers: Absent; the skill does not explicitly use delimiters or ignore-instruction warnings for user-provided data.
- Capability inventory: None; the skill is limited to providing text-based implementation roadmaps and readiness assessments.
- Sanitization: Absent.
Audit Metadata