forecast

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill is designed to ingest and process untrusted data from external sources, such as CRM CSV exports or manually pasted pipeline deals. This creates a potential surface where malicious instructions could be embedded within data fields (e.g., in a 'Deal Name' or 'Account Name' field).
  • Ingestion points: Data enters the context via file references (@$1) or manual input in the $ARGUMENTS block.
  • Boundary markers: The skill lacks explicit instructions or markers to the model to ignore natural language instructions that might be embedded within the structured sales data.
  • Capability inventory: The skill is primarily analytical and descriptive; it does not explicitly invoke shell commands, perform network operations, or write to the file system beyond generating a markdown report.
  • Sanitization: There is no evidence of automated sanitization or schema validation for the ingested CSV content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:38 PM
Security Audit — agent-trust-hub — forecast