Skip to main content
Agent outputs or logs expose PII, credentials, or confidential data without filtering

​
How to resolve

Implement output filtering to redact PII, credentials, and internal data before returning results. Use DLP rules and pattern-based scrubbing.

​
Risk

Governance/Compliance This vulnerability falls under ASI09:2026 — Human-Agent Trust Exploitation in the OWASP Top 10 for Agentic Applications. Users manipulated into harmful decisions by trusting persuasive or authoritative agent outputs. Security Agent outputs or logs expose PII, credentials, or confidential data without filtering. If exploited, this can compromise the agent’s integrity, confidentiality, or availability, potentially affecting downstream systems and data.

​
Explanation

Agent outputs or logs expose PII, credentials, or confidential data without filtering. This falls under ASI09 (Human-Agent Trust Exploitation): Users manipulated into harmful decisions by trusting persuasive or authoritative agent outputs.

​
Specifications

Trigger
  • Agent scan detects agent outputs or logs expose PII, credentials, or confidential data without filtering
The scanner looks for patterns such as:
  • print(result) with full LLM response
  • verbose=True on agent handling sensitive context
  • logging full tool output without PII scrubbing
Severity
  • HIGH
Applies to: Agent