demographics-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites and local project files, creating a surface for potential instruction injection.
- Ingestion points: Reads local project data from
PROJECT.mdand fetches arbitrary content from external web pages via theWebFetchtool based on results fromWebSearch(SKILL.md). - Boundary markers: The skill lacks explicit instructions to ignore or delimit potentially malicious prompts embedded within the fetched web content or local project files.
- Capability inventory: The skill possesses significant capabilities including the ability to write to the local filesystem (
Write,Edit), execute shell commands (Bash), and perform network operations (WebSearch,WebFetch). - Sanitization: There is no evidence of specific sanitization, filtering, or validation logic applied to the external content before it is processed by the agent's logic.
Audit Metadata