kf-g-artifacts-sanitize
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for the agent to sanitize and refine generated artifacts. It focuses on removing technical debt, conversation history, and prompt remnants to ensure final deliverables are professional and standalone. It contains no executable code, network operations, or sensitive file access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes artifacts generated within the conversation context, which could potentially include content derived from untrusted inputs. However, the skill's specific purpose is to remove sensitive remnants (instructions, constraints), and it lacks dangerous capabilities.
- Ingestion points: Current session artifacts (as described in the
## 目標section of SKILL.md). - Boundary markers: The skill does not define specific delimiters for the artifacts it processes.
- Capability inventory: Text transformation and output only; no file-system writing, network access, or command execution capabilities are present.
- Sanitization: The skill's primary logic acts as a sanitization filter to remove meta-content and production traces.
Audit Metadata