taubyte-context-log

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the execution of several CLI commands to gather project metadata, including tau version, tau --json current, and resource listing commands such as tau --json list domains and tau --json list databases.
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by aggregating data from the local environment into context log files.
  • Ingestion points: Data is pulled from the project's config/config.yaml file and the output of various tau and dream CLI commands.
  • Boundary markers: No explicit delimiters or boundary markers (e.g., specific tags or 'ignore' instructions) are specified for the data being written to the log files.
  • Capability inventory: The skill possesses the capability to execute shell commands (tau, dream) and perform file-write operations within the project directory (.taubyte_ai/context.log.md, .taubyte_ai/logs.txt).
  • Sanitization: The instructions do not include steps to sanitize or validate the ingested data before it is recorded in the project's persistent logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 04:24 PM
Security Audit — agent-trust-hub — taubyte-context-log