consultant
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from external sources (web search) and user inputs, which it then persists to the local file system.
- Ingestion points: Untrusted data enters the context during Step 4 (ANALYZE) via web search and user-provided context as defined in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or 'ignore embedded instructions' warnings for processed data.
- Capability inventory: The skill instructs the agent to persist research findings to the local file system (
analysis/directory) and facilitates handoffs to other delivery skills. - Sanitization: There are no instructions for sanitizing, escaping, or validating external content before it is persisted or incorporated into the final synthesis.
Audit Metadata