helium-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external sources such as news articles and remote URLs into the agent's context.
- Ingestion points: Tools such as
get_bias_from_urlandsearch_newsallow the agent to fetch and process content from arbitrary web addresses and search results (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the retrieved news content or URLs.
- Capability inventory: The skill provides data retrieval and analysis tools via the Model Context Protocol; it does not explicitly define file-system write operations or local subprocess execution.
- Sanitization: There is no evidence of sanitization or validation of the content returned from the external news sources or analyzed URLs.
Audit Metadata