asc-ad-hoc-distribution

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the asc CLI tool and jq to perform operations like planning, applying, and publishing iOS builds, as well as inspecting JSON artifacts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from configuration files (config.json, devices.json) and remote responses from App Store Connect or S3-compatible storage, which are then used to generate deployment plans and execute distribution workflows.
  • Ingestion points: Processes config.json, devices.json, and .asc/distribution/plan.json from the local file system.
  • Boundary markers: Implements a "plan and apply" workflow that requires the agent to inspect a planHash and wait for explicit confirmation of the exact effects inventory before executing side effects.
  • Capability inventory: Performs network operations (App Store Connect API, S3 uploads) and file system writes (writing plans, link artifacts, and distribution states) via the asc tool.
  • Sanitization: Relies on structured JSON schemas and a 64-character hash confirmation mechanism to ensure the integrity of the distribution plan between the planning and execution stages.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:32 PM