asc-whats-new-writer
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
gitto retrieve commit history and theascCLI tool to manage App Store metadata. These operations are functional requirements for the skill's purpose. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it ingests untrusted data from git logs and user-provided text. This data is used to generate the 'What's New' text, which is eventually uploaded to the App Store.
- Ingestion points: Git commit messages and user-provided descriptions in 'Phase 1: Gather Input'.
- Boundary markers: No explicit delimiters or instructions are used to isolate the untrusted input from the agent's instructions or to warn the agent about embedded instructions.
- Capability inventory: The skill has the capability to execute shell commands (
git,asc) and perform updates to App Store metadata (write access). - Sanitization: There is no evidence of sanitization, filtering, or validation of the input text before it is processed by the model to generate the release notes.
Audit Metadata