article-writing
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of text-based guidelines for article writing. No malicious patterns, command execution, or unauthorized network requests were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to the ingestion of external data.\n
- Ingestion points: The skill instructs the agent to analyze user-supplied materials like published articles, newsletters, and social media posts to capture a specific voice (SKILL.md).\n
- Boundary markers: The instructions do not include specific delimiters or guidelines to ignore instructions that may be embedded in the provided writing samples.\n
- Capability inventory: The skill is limited to text generation tasks and does not have access to tools, the file system, or network capabilities.\n
- Sanitization: There is a quality gate requirement to verify factual claims, but no specific mechanisms to filter out malicious prompt injection payloads in the input data.
Audit Metadata