content-research-writer

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, exfiltration code, or dangerous command executions were detected. The skill instructions focus on assisting the user with content creation tasks such as outlining, drafting, and citation management.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to ingest and process external data during the research phase and review user-provided drafts. However, given the limited capabilities of the skill (restricted to markdown text generation and feedback), the risk is minimal.
  • Ingestion points: User drafts (e.g., article-draft.md) and information retrieved from external sources during research.
  • Boundary markers: The skill does not specify explicit boundary markers or delimiters for separating external data from instructions.
  • Capability inventory: Capabilities are limited to generating and refining markdown text. The skill does not have access to shell execution, sensitive file systems, or unauthorized network protocols.
  • Sanitization: No specific sanitization or validation logic is applied to the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 04:39 PM