article-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze external articles, which creates a surface for indirect prompt injection where malicious instructions hidden in the analyzed text could influence the agent's behavior.
- Ingestion points: Untrusted article content provided by the user or fetched during analysis.
- Boundary markers: Absent. The skill does not define structural delimiters to isolate the article content from the analysis instructions.
- Capability inventory: The skill performs web searches for fact-checking and writes output to the local file system (
analysis.md). - Sanitization: Absent. No mechanisms for escaping or validating the input text are mentioned.
Audit Metadata