flag-experiment

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to construct shell commands by interpolating user-provided inputs, such as <flag-id> and <experiment-id>, directly into command strings for the gb-call tool. This pattern presents a potential risk of shell command injection if the user-supplied identifiers contain shell metacharacters.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes external data from the GrowthBook API, which could contain instructions aimed at manipulating the agent's behavior.
  • Ingestion points: External data enters the agent's context through the responses of gb-call GET /api/v2/features/<flag-id> and gb-call GET /api/v1/experiments/<experiment-id> (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers are employed to isolate the data retrieved from the API from the agent's instructions.
  • Capability inventory: The skill allows the agent to execute shell commands via the gb-call script to modify flag rules and configurations (SKILL.md).
  • Sanitization: The skill does not specify any sanitization, validation, or escaping procedures for the content returned by the API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 02:28 PM
Security Audit — agent-trust-hub — flag-experiment