skills/coinbase/cds/git.repo-manager/Gen Agent Trust Hub

git.repo-manager

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from external Git repositories via git clone and git pull. This behavior is the primary stated purpose of the repository manager and is confined to a local cache directory.
  • [COMMAND_EXECUTION]: Employs Bash commands to perform repository lifecycle operations. These operations are restricted to the temp/repo-cache/ directory, as enforced by the skill's logic and the allowed-tools configuration.
  • [PROMPT_INJECTION]: Identified an attack surface for indirect prompt injection because the skill ingests untrusted data from external repositories. However, the skill's scope is limited to mechanical filesystem operations and does not include instructions for the agent to process or interpret the repository's contents.
  • Ingestion points: External repositories accessed via git clone and git pull in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Git and filesystem operations defined in SKILL.md.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 02:34 AM
Security Audit — agent-trust-hub — git.repo-manager