knowledge-query
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied queries to search a knowledge base, creating a surface for indirect prompt injection.
- Ingestion points: User keywords or questions provided as input (SKILL.md, references/examples.md).
- Boundary markers: Absent; instructions do not explicitly tell the agent to ignore instructions embedded in the user's query data.
- Capability inventory: Knowledge base search (semantic search). No file system writing, network exfiltration, or dynamic code execution capabilities are present in the skill configuration.
- Sanitization: Absent; the skill relies on the agent's internal safety filters for user input.
Audit Metadata