content-research-writer
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill provides clear instructions for a collaborative writing partner and does not contain any suspicious shell commands, network operations, or encoded content.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an inherent attack surface for indirect prompt injection as it is designed to ingest research data from external sources and process user-provided text. This risk is minimized by the skill's primary focus on writing assistance rather than executing sensitive system actions.
- Ingestion points: Research findings extracted from web sources and user-provided draft sections.
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded in research data.
- Capability inventory: The skill uses standard agent search capabilities for research and file operations (mkdir, touch, read/write) for local drafting.
- Sanitization: No specific content filtering or sanitization of external research data is described.
Audit Metadata