logokit

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data fields including 'brandName', 'tagline', and 'keywords' as seen in the 'Brand Brief Parameters' section of SKILL.md. It lacks explicit boundary markers to delimit user-provided content and does not describe sanitization procedures, creating an indirect prompt injection surface.
  • [COMMAND_EXECUTION]: The documented workflow involves subprocess calls to 'mkdir' and 'curl' where user-provided variables like '{brandName}' are interpolated directly into file system paths. This pattern presents a surface for directory traversal attacks if the inputs are not validated before execution.
  • [DATA_EXFILTRATION]: The skill performs network requests to 'api.logokit.app' for API communication and downloading image assets. These requests target vendor-owned infrastructure associated with the 'pirika-dev' author and do not involve access to sensitive local credentials or system files, making the network activity consistent with the skill's intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 11:04 AM