Explorium Enrichment

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or high-risk behaviors were detected. The skill uses defined edge functions and requires specific capabilities ('explorium_api', 'ops_tables') consistent with its stated purpose of data enrichment.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes data from external sources.
  • Ingestion points: Data enters the agent context from existing Ops tables (via 'table_id') and external responses from the Explorium API.
  • Boundary markers: The skill instructions do not specify the use of delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The skill utilizes the 'explorium-enrich' edge function, which has the capability to write enriched data back to Ops tables.
  • Sanitization: There is no mention of sanitization or validation of the data retrieved from the API or the table before it is processed or written back.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:37 AM