cpa-irs-representation
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process external, untrusted data including IRS notices, letters, and tax transcripts provided by users. This creates a surface for indirect prompt injection where an attacker could embed malicious instructions within a simulated IRS document.
- Ingestion points: The skill triggers on the receipt of IRS notices, exam documents, and transcripts.
- Boundary markers: The instructions lack explicit boundary markers or directives for the agent to disregard instructions embedded within the analyzed documents.
- Capability inventory: The skill provides logic and checklists but does not invoke external tools or scripts directly within the provided file.
- Sanitization: There is no evidence of content sanitization or validation of the ingested documents. This risk is considered inherent to the skill's primary function of document analysis and is documented as safe within this specific context.
Audit Metadata