shatter
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not include any executable scripts, binaries, or configuration files that could perform unauthorized actions.
- [SAFE]: The content defines a structured workflow for chaos engineering that includes mandatory safety steps, such as defining containment boundaries (blast radius), requiring ownership verification, and establishing rollback plans.
- [SAFE]: No patterns of prompt injection, data exfiltration, or obfuscation were detected in the skill instructions or YAML metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze a user-provided target (codebase or system) which serves as an ingestion point for untrusted data.
- Ingestion points: The system, plan, or codebase provided by the user in the target description.
- Boundary markers: The procedure requires the agent to restate 'no-touch boundaries' before taking action (Step 1).
- Capability inventory: The skill uses the agent's existing toolset; no additional tools or network capabilities are requested.
- Sanitization: No explicit sanitization or filtering of the target data is defined in the instructions.
Audit Metadata