create-dataflow-approximation

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the opentaint test approximation run command to validate dataflow models. This is a legitimate operation for the skill's stated purpose of testing approximations against a project.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes data from external files to generate code.
  • Ingestion points: Reads dropped-external-methods.yaml and .opentaint/test-results/<name>/test-result.json to identify methods and test failures.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are used when reading these files.
  • Capability inventory: The agent can write Java files and execute shell commands via the opentaint CLI.
  • Sanitization: The skill does not describe any sanitization or validation of the content read from the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:39 AM
Security Audit — agent-trust-hub — create-dataflow-approximation