media-writing
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- NO_CODE (SAFE): The skill is composed entirely of markdown instructions and metadata. No scripts (Python, JavaScript, etc.) or executable components are present.
- PROMPT_INJECTION (SAFE): The instructions define a specific professional role and formatting guidelines. No attempts to bypass safety guardrails, override system prompts, or extract internal instructions were identified.
- DATA_EXFILTRATION (SAFE): There are no commands or logic for accessing sensitive local files or performing unauthorized network requests. The citation instructions focus on user-provided or searched URLs for standard referencing.
- INDIRECT_PROMPT_INJECTION (LOW): The skill is designed to process external information (trending topics and sources). While this creates an ingestion surface for untrusted data, the skill lacks the capabilities (such as file-system write access or shell execution) required for high-severity exploitation. The impact is limited to the agent's reasoning and output display.
- OBFUSCATION (SAFE): All text is provided in clear, human-readable markdown without any encoding, zero-width characters, or homoglyphs.
Audit Metadata