process-dedup-review

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/run-process-dedup-review.mjs acts as a wrapper that executes the tiangong CLI. This is the primary intended function of the skill for administrative data processing.
  • [PROMPT_INJECTION]: The skill is designed to process external JSON data, which introduces a surface for indirect prompt injection.
  • Ingestion points: The agent reads duplicate-groups.json (as described in SKILL.md) containing external process metadata.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are included in the prompt instructions.
  • Capability inventory: The skill can execute CLI commands and write artifacts to the local filesystem.
  • Sanitization: There is no evidence of sanitization for the input JSON fields before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 06:57 AM
Security Audit — agent-trust-hub — process-dedup-review