testerarmy-cli
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes test steps, goals, and project information which could contain malicious instructions designed to influence agent behavior. The agent has the capability to execute shell commands through the
taCLI to interact with cloud testing services.\n - Ingestion points: Test definitions, descriptions, and exploration goals provided in commands like
ta tests createandta discover(SKILL.md).\n - Boundary markers: No explicit delimiters or instructions are used to isolate untrusted data or warn the agent to ignore embedded instructions.\n
- Capability inventory: Subprocess calls to the
tautility for managing tests and projects, as well as network communication with the TesterArmy cloud service.\n - Sanitization: No evidence of sanitization or validation of processed input strings.
Audit Metadata