skills/helderberto/agent-skills/ship/Gen Agent Trust Hub

ship

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard version control operations including git commit, git push, and git pull. These operations are used as intended for repository management and are restricted to the local environment and configured remotes.
  • [DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the !git status, !git diff HEAD, and !git log syntax to automatically populate the agent's context with current repository information. These commands are benign, intended for workflow context, and do not involve unauthorized file access or network exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the repository's history and current changes, which could theoretically contain malicious instructions.
  • Ingestion points: Repository metadata and code changes loaded via git diff and git log commands.
  • Boundary markers: While no specific text delimiters are used, the workflow enforces a strict security gate via the safe-repo skill to detect secrets and malicious patterns.
  • Capability inventory: The skill possesses the ability to write to the file system (git commit) and interact with remote servers (git push).
  • Sanitization: Potential risks are mitigated by a mandatory pre-launch gate that performs a sensitive data scan and code validation before any changes are finalized or pushed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 06:03 PM
Security Audit — agent-trust-hub — ship