laststance-publish-skill

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard shell commands such as mkdir, cp, and git to manage skill files and update a repository.
  • [COMMAND_EXECUTION]: The instructions include the use of npx skills, which executes the skills CLI package to manage skill installations and symlinks.
  • [DATA_EXFILTRATION]: The skill moves files from local agent directories (~/.claude/skills/) to a remote repository. This behavior is consistent with the skill's stated purpose of publishing content to a central repository owned by the author.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 03:29 AM
Security Audit — agent-trust-hub — laststance-publish-skill