skills/sanxzy/skills/bd-review/Gen Agent Trust Hub

bd-review

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks detected. The skill's functionality is limited to performing local code and documentation reviews and writing issue reports to a designated directory within the workspace.
  • [SAFE]: The skill exhibits an indirect prompt injection surface as it is designed to process external code changes and implementation reports. However, the risk is considered safe as its capabilities are restricted to analysis and local file logging.
  • Ingestion points: Instructions to read 'actual code changes' and 'implementation report' in SKILL.md.
  • Boundary markers: No delimiters or warnings specified for external content.
  • Capability inventory: The skill uses file reading and local file writing for reporting issues to the .plans/ directory.
  • Sanitization: No sanitization or validation of the ingested code or report content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 04:28 AM
Security Audit — agent-trust-hub — bd-review