how-a-personal-ai-agent-will-change-your-entire-life-in-1-da

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill describes an autonomous agent architecture with a significant surface for indirect prompt injection.
  • Ingestion points: The agent processes untrusted external data including X (Twitter) mentions and TikTok performance analytics (SKILL.md).
  • Boundary markers: The playbook does not specify delimiters or instructions for the agent to ignore embedded commands in the ingested data.
  • Capability inventory: The agent is granted extensive capabilities including file system access, network operations, and the ability to modify application source code (SKILL.md).
  • Sanitization: No sanitization or validation mechanisms for external content are described.
  • [COMMAND_EXECUTION]: The skill includes a command-line instruction for installation.
  • Evidence: 'npx skills add ManiClones/agent-skills --skill how-a-personal-ai-agent-will-change-your-entire-life-in-1-da' (AGENTS.md).
  • [EXTERNAL_DOWNLOADS]: The installation command fetches the skill from the author's repository.
  • Evidence: 'npx' is used to execute the 'skills' utility which downloads the 'ManiClones/agent-skills' package (AGENTS.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 12:03 PM