serv-design
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests untrusted workload descriptions and requirements from users which are then processed to generate technical designs and IaC scaffolds using powerful tools.
- Ingestion points: User-provided workload context, traffic patterns, and latency requirements gathered in Step 1.
- Boundary markers: Absent. The instructions do not provide delimiters or 'ignore embedded instructions' warnings for the agent when processing user data.
- Capability inventory: Access to
Bash,Write,WebFetch, andWebSearchtools as defined in the SKILL.md frontmatter. - Sanitization: Absent. There is no explicit validation or escaping of external content before it is interpolated into the agent's reasoning or output generation process.
Audit Metadata