vp-clear-writing
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill is entirely instructional and documentation-oriented, designed to improve the quality of AI-generated prose.
- [INDIRECT_PROMPT_INJECTION]: As the skill is designed to process, revise, and summarize untrusted user-provided text (such as pull request descriptions, code comments, and documents), it naturally possesses an indirect prompt injection surface.
- Ingestion points: Any text provided to the agent for editing or summarization as per the instructions in
SKILL.md. - Boundary markers: The skill explicitly instructs the agent to treat authoring instructions as constraints to be satisfied rather than content to be repeated, which aids in maintaining the boundary between instructions and data.
- Capability inventory: The skill does not request or utilize any sensitive tool capabilities (e.g., shell execution, network requests, or file system modifications).
- Sanitization: No specific technical sanitization is defined, as the skill relies on the underlying model's safety guardrails and the instructional context to handle input safely.
- [EXTERNAL_DOWNLOADS]: The skill contains numerous links to well-known technology documentation and industry-standard diagramming tools.
- Evidence: References to Mermaid, D2, Graphviz, PlantUML, draw.io, and Google/Microsoft developer style guides in the
references/folder. - Context: These references are for documentation and tool selection purposes and do not involve the execution of untrusted remote code.
Audit Metadata