research-git

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the discovery and analysis of external content, creating a surface for indirect prompt injection. Ingestion points: The fetch_repo_assets.sh script downloads files from public GitHub repositories into the local environment. Boundary markers: There are no automated mechanisms or delimiters to sanitize or ignore instructions within the fetched repository content. Capability inventory: The skill provides scripts that can execute shell commands and write to the local file system. Sanitization: No sanitization of the downloaded repository data is implemented.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with well-known and legitimate services to gather repository metadata and assets. It uses the gh CLI for GitHub API access and curl for services like OpenSSF Scorecard, OSS Insight, and deps.dev.
  • [COMMAND_EXECUTION]: The skill includes bash scripts that utilize standard command-line tools such as gh, curl, jq, grep, and sed to automate the research process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 09:10 PM
Security Audit — agent-trust-hub — research-git