qe-technical-writing
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains benign instructional content focused on improving technical writing quality, structuring blog posts, and editing documentation. The YAML frontmatter is correctly scoped and descriptive.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it is designed to ingest and process external source code and documentation files. However, this is inherent to its primary purpose of documentation generation.
- Ingestion points: Processes external files such as
src/services/PaymentService.ts,README.md, anddocs/api.mdas shown in the Agent Integration examples. - Boundary markers: None specified in the provided integration snippets.
- Capability inventory: Limited to file reading and delegation of documentation tasks to other internal agents (
qe-quality-analyzer,qe-api-contract-validator). - Sanitization: Not explicitly mentioned in the integration logic, though the skill focuses on content clarity and technical accuracy.
Audit Metadata