gap-check
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from the conversation history to drive external research actions, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads the 'settled scope' and 'technical components' from the current conversation context (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or safety warnings to ignore embedded instructions within the processed plan data.
- Capability inventory: The skill has the capability to launch 'search-specialist' agents to query external sources based on user-influenced data (SKILL.md).
- Sanitization: No sanitization or validation of conversation content is performed before it is interpolated into prompts for the research agents.
Audit Metadata