timeless-scheduling

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the curl command-line tool to interact with the Timeless API. These commands are used to fetch user configuration and create meeting invites via POST requests to my.timeless.day.
  • [DATA_EXFILTRATION]: The agent is instructed to extract meeting details (purpose, attendees, duration) from user communications and transmit this data to the my.timeless.day domain. This is consistent with the primary purpose of the skill.
  • [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by design, as it requires the agent to read and process untrusted content from external communication channels.
  • Ingestion points: The Context Gathering section in SKILL.md identifies email threads, Slack, Telegram, and calendar history as data sources.
  • Boundary markers: The instructions do not define boundary markers or delimiters to isolate untrusted external content from the agent's instructions.
  • Capability inventory: The skill possesses the capability to execute shell commands (curl) to create remote API resources based on extracted data.
  • Sanitization: There are no instructions for sanitizing or validating the extracted text before it is used to populate API request payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:20 PM
Security Audit — agent-trust-hub — timeless-scheduling