skills/aeonfun/aeon/submit-hook/Gen Agent Trust Hub

submit-hook

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Python helper script (submit-univ4.py) which in turn uses the system's git and gh (GitHub CLI) tools to manage repository updates and pull requests.
  • [EXTERNAL_DOWNLOADS]: The skill clones the official aeonfun/univ4-hooks repository from GitHub to local temporary storage to facilitate the submission process.
  • [REMOTE_CODE_EXECUTION]: During the submission flow, the skill executes a utility script (scripts/aggregate.py) contained within the cloned registry repository to regenerate the aggregate listing file.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes deployment metadata from a local ledger (memory/state/hook-deploys.json) to generate descriptions and classification for the hook marketplace.
  • Ingestion points: Data is read from memory/state/hook-deploys.json, specifically hook addresses and descriptive 'briefs'.
  • Boundary markers: The skill relies on agent instructions for data mapping rather than explicit security delimiters for the ingested content.
  • Capability inventory: The skill possesses capabilities for file system writes (to the cloned registry) and network egress via the GitHub CLI.
  • Sanitization: The submit-univ4.py script implements regex validation for Ethereum addresses and sanitizes contract names into URL-safe slugs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 02:18 PM