bansos-develop-feature

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious instructions or security threats were detected in the skill contents.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run standard development commands (npm run build/lint) and uses the project-specific bansosdev CLI tool.
  • [CREDENTIALS_UNSAFE]: References the BANSOSDEV_GITHUB_TOKEN environment variable for maintainer operations, following secure secret management practices.
  • [NO_CODE]: The skill does not contain any executable scripts, only markdown instructions and configuration.
  • [PROMPT_INJECTION]: Contains an indirect prompt injection surface where the agent processes external issue URLs to automate PRs. Ingestion points: Issue URLs mentioned in SKILL.md. Boundary markers: Absent. Capability inventory: Command execution (npm), file modification. Sanitization: Absent. This behavior is documented as the primary intended function for the development workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 11:32 AM
Security Audit — agent-trust-hub — bansos-develop-feature