git-context

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes local git commands and context tools for their intended development purposes. There are no indicators of data exfiltration, obfuscation, or unauthorized access.
  • [COMMAND_EXECUTION]: Uses native git commands (git log, git show, git blame) and local MCP tools (sem, ctx) to retrieve repository metadata and analysis. All commands are restricted to local environment information retrieval.
  • [PROMPT_INJECTION]: Analysis of the attack surface for indirect prompt injection reveals a low-risk profile associated with processing repository data.
  • Ingestion points: Commit messages and logs from git log, file contents from git show, and session data from ctx search (SKILL.md).
  • Boundary markers: None present in the provided command patterns.
  • Capability inventory: Execution of local git commands and usage of specialized analysis tools (sem, ctx).
  • Sanitization: No automated sanitization of retrieved git history or session data is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 04:22 AM
Security Audit — agent-trust-hub — git-context