journalist-analyst
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is comprised solely of markdown files and does not include any executable scripts, binaries, or automated workflows that interact with the host system. All external URLs provided are to legitimate and well-known journalistic institutions and educational platforms.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a framework for analyzing external events and claims, which introduces an inherent surface for indirect prompt injection if the text being analyzed contains adversarial instructions.
- Ingestion points: The skill processes events, claims, and stories provided by the user for analysis.
- Boundary markers: The instructions do not include specific delimiters or 'ignore' directives to isolate external content.
- Capability inventory: The skill does not contain any scripts or tools for network, file system, or subprocess operations.
- Sanitization: There are no instructions for sanitizing or escaping the content of processed events.
Audit Metadata