Skills
Navigate
skills/zjandrew/te-cli/te-audience/Gen Agent Trust Hub

te-audience

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to construct commands where user-provided JSON strings are interpolated directly into shell arguments. This is a potential vulnerability surface where a malicious user prompt could attempt to manipulate the execution of the te-cli tool.\n
  • Ingestion points: The skill accepts user-defined JSON for the --conditions flag in the te-audience +predict-cluster-count command and the --events flag in the te-audience +load-audience-props command.\n
  • Boundary markers: There are no explicit boundary markers or warnings provided to the agent to treat the contents of these JSON strings as untrusted data.\n
  • Capability inventory: The skill is designed to interact with the local environment via the te-cli binary.\n
  • Sanitization: No sanitization or escaping of the user-provided JSON content is specified in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 08:44 AM