kspec-triage-inbox

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access to sensitive data were detected. The skill uses a proprietary CLI tool (kspec) for task management and triage operations.
  • [PROMPT_INJECTION]: The skill involves processing external data (inbox items and observations), which presents an indirect prompt injection surface.
  • Ingestion points: kspec inbox list and kspec meta observations (SKILL.md).
  • Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore instructions embedded in the external content.
  • Capability inventory: Shell command execution via the kspec CLI suite (e.g., kspec triage act, kspec item set, kspec batch).
  • Sanitization: Absent. No mention of content validation or sanitization before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 05:42 PM
Security Audit — agent-trust-hub — kspec-triage-inbox