gdd
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for documentation style editing and performs its tasks as described. Analysis of the instructions and configuration reveals no patterns of prompt injection, data exfiltration, or unauthorized command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text and files, which is an inherent attack surface for indirect prompt injection. However, the instructions constrain the agent to specific stylistic transformations, and no dangerous capabilities (like network access) are exposed.
- Ingestion points: Processes file content from named paths or inline text provided in the user prompt.
- Boundary markers: Not explicitly defined within this skill; relies on the underlying agent's handling of file reads and text blocks.
- Capability inventory: File system modification (editing files in place) and agent/subagent invocation for long files.
- Sanitization: No explicit sanitization of input text is performed before processing.
Audit Metadata