israeli-client-payment-chaser

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources (invoices) and processes it with powerful capabilities.\n
  • Ingestion points: In SKILL.md and SKILL_HE.md (Step 1), the agent is instructed to import invoice data from external files or manual input.\n
  • Boundary markers: The instructions do not define delimiters or provide warnings to the agent to ignore any embedded instructions within the processed invoice data.\n
  • Capability inventory: The agent has access to Bash(python:*) for arbitrary command execution and WebFetch for network requests.\n
  • Sanitization: There is no requirement for the agent to sanitize or validate the imported data before using it to generate reports or communications.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 11:09 AM