developer-certification-program
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional and consultative. It guides the AI agent through a structured process to design certification charters using local reference files.
- [PERSISTENCE]: The skill implements a state-management mechanism by instructing the agent to record task-specific context in a file named
devrel-context.md. This is an intended feature for maintaining continuity across sessions within the agent's environment and does not constitute a malicious persistence attack. - [INDIRECT_PROMPT_INJECTION]: The skill features an interactive interview workflow that processes untrusted user input. Findings: 1. Ingestion points: User input during the design interview (SKILL.md). 2. Boundary markers: None defined. 3. Capability inventory: Filesystem read/write operations for documentation access and state storage (
devrel-context.md); no network or arbitrary command execution. 4. Sanitization: No explicit sanitization of user input before storage. Given the limited capabilities and intended consultative nature, this surface is considered safe.
Audit Metadata