outcome-roadmap
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources and user inputs.
- Ingestion points: Data enters the agent context through user-provided roadmap initiatives and results from web searches for company strategy documents (SKILL.md).
- Boundary markers: There are no boundary markers or delimiters specified to distinguish instructions from external data in the prompt context.
- Capability inventory: The skill possesses the capability to perform web searches and write content to local markdown files (e.g., Outcome-Roadmap-[year].md).
- Sanitization: The instructions do not include steps to sanitize, escape, or validate the content retrieved from external sources or user input before processing it.
Audit Metadata