timely-time-tracking
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI (
@membranehq/cli) via npm. This is a legitimate tool provided by the skill's author to facilitate platform integration. - [COMMAND_EXECUTION]: The skill utilizes the
membranecommand-line interface for authentication (membrane login), connection management (membrane connection ensure), and interacting with the Timely API (membrane action run,membrane request). These commands are standard operations for this platform integration. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where it ingests data from the external Timely Time Tracking API. If an attacker controls the data within a Timely account (e.g., project descriptions or time entry notes), they could attempt to influence the agent's behavior.
- Ingestion points: Data is received through
membrane action runandmembrane requestcommands (SKILL.md). - Boundary markers: None explicitly defined in the provided instructions; the agent is expected to process the raw output.
- Capability inventory: The agent can perform network requests and manage connections via the Membrane CLI (SKILL.md).
- Sanitization: No specific sanitization or filtering of API responses is mentioned; the skill relies on the underlying LLM's inherent safety filters.
Audit Metadata