Skills
Navigate
skills/rorkai/app-store-connect-cli-skills/asc-wall-submit/Gen Agent Trust Hub

asc-wall-submit

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the asc CLI tool, interpolating user-provided inputs for --app, --link, and --name directly into the command strings. This creates a potential surface for command injection if the inputs contain shell metacharacters.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from users to modify shared project files and generate pull requests.
  • Ingestion points: User-supplied app ID, link, and name parameters in SKILL.md.
  • Boundary markers: Absent; there are no instructions for the agent to delimit or ignore instructions that might be embedded in the user inputs.
  • Capability inventory: Shell command execution via the asc CLI and modification of the local docs/wall-of-apps.json file.
  • Sanitization: Absent; the instructions do not require the agent to validate or sanitize the link or name fields before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:22 AM
Security Audit — agent-trust-hub — asc-wall-submit