circleci
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the official Membrane CLI package (
@membranehq/cli) globally via NPM to provide the necessary tooling for the integration.- [COMMAND_EXECUTION]: The agent uses themembraneCLI to perform operations such as listing connections, searching for actions, and executing them. This includes running actions that can modify CircleCI configurations or trigger pipelines.- [PROMPT_INJECTION]: A surface for indirect prompt injection exists because the skill processes untrusted data from the CircleCI API. - Ingestion points: External data enters the context through actions like
get-job-details,get-job-artifacts, andlist-project-env-vars(SKILL.md). - Boundary markers: None identified in the prompt instructions to delimit external data from instructions.
- Capability inventory: The skill can execute shell commands via the
membraneCLI and modify remote CircleCI state. - Sanitization: No explicit validation or filtering of external content is specified in the documentation.
Audit Metadata