sync-asc-skills

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs a checkout of the rorkai/app-store-connect-cli-skills repository to audit its contents for drift. This repository belongs to the skill's author.
  • [COMMAND_EXECUTION]: The skill executes the asc (App Store Connect) command-line interface to retrieve help text, schemas, and capabilities to verify current CLI behavior.
  • [PROMPT_INJECTION]: The skill ingests data from external sources (repository files and CLI outputs), which establishes a surface for indirect prompt injection.
  • Ingestion points: Content from the rorkai/app-store-connect-cli-skills repository and outputs from the asc CLI tool in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded in the audited data.
  • Capability inventory: The skill has the ability to execute shell commands (asc), access the file system (git clone, file modifications), and interact with Git to open pull requests.
  • Sanitization: No explicit validation or escaping mechanisms are mentioned for the external data ingested during the audit process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 02:42 AM
Security Audit — agent-trust-hub — sync-asc-skills