skills/iamzifei/aikey/aikey-track/Gen Agent Trust Hub

aikey-track

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill manages a tracking system that stores user-supplied data and instructions in local files for retrieval at a later date.
  • Ingestion points: The skill reads from {config.paths.tracking}/ and {config.paths.memory}/aikey-track/, which contain content generated from previous user interactions.
  • Boundary markers: Data is structured using YAML frontmatter, though explicit delimiters to prevent the agent from obeying embedded instructions within the 'action' field are not strictly enforced beyond instructional guidance.
  • Capability inventory: The skill has the capability to read and write files within the configured workspace paths.
  • Sanitization: The instructions include a requirement to avoid recording sensitive details (amounts, real names) when anonymization mode is active, reducing the risk of data leakage via stored files.
  • [SAFE]: The skill references an external repository at https://github.com/iamzifei/aikey for documentation. This is a legitimate resource associated with the skill's author (iamzifei).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 06:35 AM