experiment-stop
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local helper script
${CLAUDE_PLUGIN_ROOT}/scripts/gb-callto execute shell commands and interact with the GrowthBook API. This is the primary function of the skill and is documented as standard behavior within the vendor's environment.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by fetching experiment metadata (names, descriptions, and variations) from the GrowthBook API. Maliciously crafted data in the experiment could potentially be used to influence the agent's behavior.\n - Ingestion points: API responses from
GET /api/v1/experimentsandGET /api/v1/experiments/<id>referenced inSKILL.md.\n - Boundary markers: Absent; the instructions do not implement delimiters or warnings to differentiate remote data from system-level instructions.\n
- Capability inventory: Shell command execution via the
gb-callhelper and general command-line capabilities.\n - Sanitization: The skill does not define specific validation or escaping mechanisms for the data retrieved from the remote API before processing.
Audit Metadata