skills/huntie/skills/commit-cloud/Gen Agent Trust Hub

commit-cloud

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute specific local scripts, scripts/commit-cloud and scripts/pull, to manage the backup and restoration of development work. These are assumed to be part of the user's project environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the synchronization of external repository data, which represents an ingestion surface for untrusted content.
  • Ingestion points: Content is pulled from a remote repository into the local .commit-cloud/ directory during restoration.
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are mentioned for the data being restored.
  • Capability inventory: The skill performs file system writes and network operations via its backup and pull scripts.
  • Sanitization: No explicit sanitization or verification of the metadata or commit content within the synchronized stacks is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 02:10 PM