devrel-dx-craft
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is comprised of Markdown documentation and YAML/JSON configuration files. It contains no executable scripts, binaries, or package dependencies in any of the provided files.
- [SAFE]: Analysis of the instructions and reference materials confirms the absence of malicious patterns such as prompt injection, hardcoded credentials, data exfiltration, or obfuscation.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit user-supplied developer documentation and content plans, creating a potential surface for indirect prompt injection.
- Ingestion points: The agent ingests user-provided text describing "getting-started experiences", "onboarding flows", and "content plans" as specified in
SKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands in user data are provided, though the agent is required to cite internal reference rules.
- Capability inventory: The skill does not define or utilize any dangerous tools, network operations, or file-writing capabilities.
- Sanitization: No sanitization or validation logic is present for the processed user content.
Audit Metadata