competitive-landscape
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external websites and existing local documents, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: Data is gathered from web search results and local markdown files located in the competitive/, market/, research/, and strategy/ directories.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore potentially malicious instructions embedded within the retrieved external information.
- Capability inventory: The skill has the ability to read from and write to the local file system (saving analysis as markdown) and perform network operations via a web search tool.
- Sanitization: There are no documented steps for sanitizing or validating the content retrieved from external sources before it is processed or saved.
Audit Metadata