bs-skill-bootstrap

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell scripts (tools/validate.sh, tools/sync.sh) to perform its core functions of validation and synchronization. These are standard developer tools within the project environment.
  • [PROMPT_INJECTION]: While the skill contains strong imperative language (e.g., 'Do not skip any step for any reason', 'Hard Rules override everything'), these are functional instructions for the agent to follow a specific workflow and do not attempt to bypass safety guidelines or extract system prompts.
  • [DATA_EXFILTRATION]: The skill reads from local configuration files like skills.json and external/sources.yaml to check for name collisions and existing solutions. It does not perform any network operations to non-whitelisted domains or send sensitive data externally.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 03:30 AM
Security Audit — agent-trust-hub — bs-skill-bootstrap