automating-api-testing

Warn

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/generate_test_suite.py script contains functionality to generate shell scripts from provided content and apply executable permissions using chmod(0o755). This dynamic code generation allows the agent to create and run arbitrary bash scripts.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through the ingestion of external data.\n
  • Ingestion points: The skill instructions in SKILL.md direct the agent to parse external OpenAPI and GraphQL specification files.\n
  • Boundary markers: There are no explicit delimiters or instructions for the agent to treat the content of these specifications as data rather than instructions.\n
  • Capability inventory: The skill has the capability to write files, modify permissions, and execute shell commands via the Bash tool.\n
  • Sanitization: The skill does not implement or describe any sanitization or validation of the data extracted from API specifications before it is used for code generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 21, 2026, 11:30 AM
Security Audit — agent-trust-hub — automating-api-testing