skills/modem-dev/hunk/hunk-review/Gen Agent Trust Hub

hunk-review

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill enables interaction with the local hunk CLI tool. It utilizes hunk session commands to inspect and control live diff review sessions, including the ability to reload session content with subcommands like diff or show.\n- [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by processing untrusted repository data via diff inspection commands. It lacks explicit instructions for sanitization or the use of boundary markers when interpreting this data.\n
  • Ingestion points: Repository diff content is ingested through hunk session review --json and hunk session review --include-patch (SKILL.md).\n
  • Boundary markers: Absent. No delimiters or instructions to ignore embedded content are provided.\n
  • Capability inventory: The skill provides CLI execution capabilities via the hunk session command set, including navigation and session reloading (SKILL.md).\n
  • Sanitization: Absent. The skill does not describe any validation or filtering of the processed diff data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 07:05 PM
Security Audit — agent-trust-hub — hunk-review