developer-quickstart-guide
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a workflow for auditing and rewriting existing documentation provided by users. This ingestion of external, untrusted content represents a surface for indirect prompt injection.
- Ingestion points: Documentation content provided by the user for the 'Audit' workflow and user input during the 'Interview' phase (SKILL.md).
- Boundary markers: The agent is constrained by a specific 'Expected output shape' and a predefined 'quickstart-template.md' for generating its responses.
- Capability inventory: The skill is limited to text analysis and generation; it does not request tool access for filesystem manipulation, network requests, or shell execution.
- Sanitization: The instructions explicitly mandate 'Copy-paste rules' (SKILL.md) that require the agent to strip shell prompts and use unmistakable placeholders (e.g.,
<YOUR_API_KEY>) to ensure the generated documentation is safe and functional.
Audit Metadata