clari-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external revenue data exports which serves as a potential vector for indirect prompt injection if those exports contain malicious content.\n
  • Ingestion points: Untrusted data is processed through the forecasts, actuals, entries, current, and previous list parameters in the Python scripts defined in SKILL.md.\n
  • Boundary markers: The instructions lack specific delimiters or boundary markers to ensure the agent ignores instructions that may be embedded within the data.\n
  • Capability inventory: The skill uses Bash(python3:*) to execute the data analysis logic.\n
  • Sanitization: The logic processes data assuming a valid schema but does not implement content sanitization or validation to filter out potential instructions within data fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 01:17 PM
Security Audit — agent-trust-hub — clari-core-workflow-b