App Store Changelog

Create user-facing App Store release notes by collecting and summarizing all user-impacting changes since the last git tag (or a specified ref). Use when ask...

This skill appears coherent and limited in scope, but review these practical points before installing: (1) it runs git commands and prints repo root, commit summaries, and file paths — only use it on repositories you trust because commit messages or paths can include sensitive info; (2) the agent will need to interpret commit messages and touched files to decide what is 'user-facing' — ask for clarification when ambiguous; (3) there are no network calls or credential requests in the provided files, but if the skill is later modified to call external services, re-check for unexpected endpoints; (4) you can safely inspect or run scripts/collect_release_changes.sh locally to see exactly what it prints before giving the agent access.

Type: OpenClaw Skill Name: toby-app-store-changelog Version: 1.0.0 `, it's still just one string in the variable. In Bash, if you don't quote it, it undergoes word splitting. So `v1..v2 --output=file` becomes two arguments: `v1..v2` and `--output=file`. This is exactly how argument injection works. Okay, I'm done. `suspicious`. Wait, I'll make the summary more concise. "The skill bundle is classified as suspicious due to a lack of input sanitization in the `scripts/collect_release_changes.sh` script. The script uses unquoted variables when executing `git log` commands, which creates a vulnerability to argument injection. An attacker could potentially provide a malicious reference name containing flags like `--output` to overwrite sensitive files. Despite this flaw, the skill's overall design and instructions in `SKILL.md` and `references/release-notes-guidelines.md` are well-aligned with its stated purpose of generating App Store release notes." Actually, the prompt says "1 short paragraph. Mention the 1–3 most important indicators and the specific file names involved." Indicators: 1. Argument injection vulnerability (lack of sanitization). 2. Potential for unauthorized file writes via `git log --output`. 3. File: `scripts/collect_release_changes.sh`. Final Summary: The skill bundle is classified as suspicious due to a lack of input sanitization in `scripts/collect_release_changes.sh`. The script uses unquoted variables when constructing `git