timeless-api

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands for its core functionality, specifically involving tool execution.
  • Uses curl to interact with the my.timeless.day API endpoints.
  • Utilizes yt-dlp for downloading and processing YouTube video content.
  • Orchestrates local shell scripts (upload.sh, podcast.sh, youtube.sh) to handle media workflows.
  • [EXTERNAL_DOWNLOADS]: The skill fetches data and media files from remote infrastructure.
  • Connects to https://my.timeless.day for all service operations.
  • Downloads meeting recordings from signed Google Cloud Storage URLs (storage.googleapis.com).
  • Retrieves media content from third-party podcast feeds and YouTube platforms.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to the nature of its data processing.
  • Ingestion points: Processes meeting transcripts, AI summaries, and external media metadata from the Timeless API and external video/audio platforms into the agent context (SKILL.md).
  • Boundary markers: Absent. There are no explicit instructions or delimiters used to separate untrusted external content from the agent's core instructions.
  • Capability inventory: The skill possesses capabilities for network operations (curl), file system writes (/tmp, timeless-processed.json), and external media fetching (yt-dlp) across its associated scripts.
  • Sanitization: No evidence of input validation or sanitization is provided for the external data being ingested.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:20 PM
Security Audit — agent-trust-hub — timeless-api