autosync-ic-skills
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a bash synchronization script and Internet Computer skill assets from the author's official domain (
https://skills.internetcomputer.org). These downloads are used to populate the local.claude/skills/directory. - [COMMAND_EXECUTION]: The agent is instructed to execute the downloaded
sync-ic-skills.shscript to manage project files and perform an initial synchronization of the development environment. - [REMOTE_CODE_EXECUTION]: The skill implements a self-updating mechanism that ingests content from a remote repository into the agent's operational environment.
- Ingestion points: The script fetches a skill index (
index.json) and individual skill files (Markdown and scripts) from the remote vendor repository. - Boundary markers: The skill relies on the agent's native discovery of files in the
.claude/skills/directory. - Capability inventory: The synchronization script utilizes shell utilities including
curl,jq,mkdir,mv, andrmwithin the project's managed subdirectory. - Sanitization: The script includes explicit path-safety validation logic (
is_safe_nameandis_safe_relpath) to ensure that downloaded filenames and paths do not attempt to escape the designated skills directory. - [SAFE]: The provided synchronization script follows defensive coding best practices, such as utilizing the
${VAR:?}bash pattern to prevent destructive command execution in the event of unset variables. Additionally, it uses atomic file swaps with backups and strictly adheres to the platform's user-trust model by requiring manual confirmation for the session start hook.
Audit Metadata