skills/nickcrew/claude-cortex/git-ops/Gen Agent Trust Hub

git-ops

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git operations as direct shell commands using the bash tool. This is the primary method for executing operations like status, add, commit, push, and pull as defined in references/git.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from the repository environment, such as diffs and logs, to provide workflow guidance and generate commit messages. This creates a surface for indirect prompt injection.
  • Ingestion points: Repository state, working directory changes, and git logs are analyzed during the Analyze step in references/git.md.
  • Boundary markers: No specific delimiters or instruction-ignore markers are specified for the ingested content.
  • Capability inventory: Operations include bash for git commands, read for state analysis, grep for log parsing, and write for message generation.
  • Sanitization: No explicit sanitization or escaping of diff content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 12:41 PM
Security Audit — agent-trust-hub — git-ops