mksc-writing-style
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided academic manuscripts, which constitutes an ingestion surface for untrusted data. However, the risk is negligible as the skill only performs text analysis and rewriting within the agent's context and lacks capabilities for network access, arbitrary command execution, or file system modifications.
- Ingestion points: Processes manuscript prose for style evaluation and rewriting (SKILL.md).
- Boundary markers: Not explicitly defined for the manuscript input.
- Capability inventory: Limited to text processing, comparison against style guidelines, and outputting an evaluation ledger.
- Sanitization: Not present, but not required for this low-privilege task.
Audit Metadata