kero-scope
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes a "product thesis" and research findings (external, untrusted data sources) to generate feature lists, which constitutes an indirect prompt injection surface.
- Ingestion points: The description and "Tracing" section confirm the skill ingests a "product thesis" and "research" content from the agent's context or filesystem.
- Boundary markers: The instructions do not specify any boundary markers or instructions to treat the ingested data as untrusted, which could allow instructions embedded in the thesis to influence agent behavior.
- Capability inventory: The skill directs the agent to write output to the local file system (
docs/scope.md). - Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from the thesis before it is processed or written to disk.
Audit Metadata