skills/xoai/sage/pack-validate/Gen Agent Trust Hub

pack-validate

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes a local shell script located at .sage/tools/sage-check-pack.sh to perform automated quality checks on pack files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external 'pack-files' and 'test prompts'. This represents a potential surface for indirect prompt injection if the files contain malicious instructions. However, this is part of the intended validation workflow and no specific bypass patterns were detected.
  • Ingestion points: Reads packs/<pack-name>, test prompts, and observation-report in SKILL.md.
  • Boundary markers: None specified in instructions.
  • Capability inventory: Executes bash scripts and writes to the filesystem via .sage/pack-build/validation.md (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the input data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 01:31 AM
Security Audit — agent-trust-hub — pack-validate