orbtrack-triage

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard filesystem commands such as ls and mv to manage and categorize files located within a directory path defined by the $VAULT environment variable. These operations are aligned with the skill's stated purpose of file triage.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a processing engine for untrusted data residing in the OrbTrack staging area.
  • Ingestion points: Reads files and folder structures from $VAULT/memorbs/HQ/OrbTrack/ (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the files being triaged.
  • Capability inventory: The agent can list files, move them to different directories, update frontmatter content, and hand off data to other specialized skills like business-card-ingestion or recording-transcription (SKILL.md).
  • Sanitization: No explicit sanitization or filtering of the note content is described before processing or moving.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 09:47 AM
Security Audit — agent-trust-hub — orbtrack-triage