catch-up
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which creates a potential surface for indirect prompt injection. This is a common characteristic of skills that summarize external content.
- Ingestion points: The skill ingests untrusted data from the
explainx.aiMCP server and from web search results (vendor blogs, release notes). - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded within the retrieved news content.
- Capability inventory: The skill has read access to local project files (
package.json,requirements.txt, etc.) and the ability to call external tools (MCP servers and web search). It does not have capabilities to write to the file system or execute arbitrary code. - Sanitization: No explicit sanitization or filtering of the retrieved content is mentioned prior to reporting it to the user.
Audit Metadata