repo-scan

Warn

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's installation process fetches source code from an unverified community repository at https://github.com/haibindev/repo-scan.git. This source is not from a recognized or established organization.
  • [COMMAND_EXECUTION]: The installation workflow requires the execution of multiple shell commands, including git init, git remote, git fetch, and cp -r, to download and move external code into the skill environment.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it ingests untrusted code from files during its audit process. 1. Ingestion points: broad reading of every file in the target repository (SKILL.md). 2. Boundary markers: absent from the instructions. 3. Capability inventory: reads files to detect libraries and assign verdicts. 4. Sanitization: no mention of escaping or validation of the processed file content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 12:20 AM
Security Audit — agent-trust-hub — repo-scan