skills-collection-manager

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill's bulk-download scripts (e.g., bulk-download-skills.sh and download-top-repos.sh) clone arbitrary GitHub repositories listed in repos.txt or REPOS and then read and process SKILL.md files from those public repos, which are untrusted third-party/user-generated content the agent ingests and interprets as part of its workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The bulk-download scripts perform git clone at runtime of repositories such as https://github.com/anthropics/claude-code-skills (and other GitHub URLs listed) and copy SKILL.md files into the collection, meaning remote content fetched at runtime can directly supply agent prompts/instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:51 PM