reviewing-technical-prose
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill strictly focuses on technical writing standards and quality control.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a technical prose editor, which involves processing external and potentially untrusted text documents. This creates a surface for indirect prompt injection where instructions embedded in the reviewed text could influence the agent. The risk is minimized by instructions that constrain the agent to "running prose" and forbid modification of functional elements like code blocks or link targets.
- Ingestion points: External technical documents processed for review and rewriting as described in
SKILL.md. - Boundary markers: None explicitly defined in the prompt instructions to separate the source text from the agent's instructions.
- Capability inventory: The skill defines no subprocess calls, file-writing operations, or network requests across its instructions.
- Sanitization: No specific sanitization or filtering logic is provided for the external text input.
Audit Metadata