langgraph-workflows

Warn

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The calculator tool in Pattern 3 uses Python's eval() function to execute logic based on strings generated from agent messages. This pattern allows for the execution of arbitrary Python code on the host machine if the model is influenced by untrusted input to generate malicious expressions.- [INDIRECT_PROMPT_INJECTION]: The skill architecture allows untrusted user data to reach a code execution sink via the agent state machine without sufficient isolation.
  • Ingestion points: User-provided messages stored in the messages list within the AgentState TypedDict in SKILL.md.
  • Boundary markers: Absent. The graph patterns do not implement delimiters or specific system instructions to prevent the model from obeying instructions embedded within user content.
  • Capability inventory: Arbitrary code execution capability via the eval() call in the calculator tool defined in SKILL.md.
  • Sanitization: The skill lacks any input validation, filtering, or escaping for the expression parameter before it is passed to the execution sink.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 31, 2026, 01:19 PM
Security Audit — agent-trust-hub — langgraph-workflows