list-enrichment
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions as an orchestrator that takes data from company tables and uses it to construct research prompts. This creates a surface for indirect prompt injection where malicious instructions in the source data (e.g., a website's metadata) could attempt to influence the research output.
- Ingestion points: Company domains and row data fetched via the
extruct-apiskill as described in SKILL.md. - Boundary markers: Absent; the instructions do not specify the use of delimiters around the
{input}placeholder in the prompt guidelines. - Capability inventory: Ability to create new table columns and initiate enrichment runs via the
extruct-apiskill (SKILL.md). - Sanitization: No mention of input validation or escaping for the data being enriched.
- [SAFE]: The skill follows security best practices by delegating all state-changing operations and network requests to a dedicated core API skill, effectively reducing the direct attack surface. It also incorporates human-in-the-loop checkpoints for confirmation of enrichment parameters and quality review of the results.
Audit Metadata