skill-comparison
Warn
Audited by Snyk on Mar 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md and README explicitly instruct fetching and parsing skills from arbitrary remote URLs using scripts/fetch_skill.py, and the agent is expected to read and act on that untrusted, user-provided web content to drive comparisons and recommendations, which could enable indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill includes scripts/fetch_skill.py which at runtime fetches remote SKILL.md files (e.g., https://example.com/skill/SKILL.md or https://github.com/user/repo/skills/data-viz/SKILL.md) and injects that fetched content into the agent's parsing/analysis flow, meaning external content fetched at runtime can directly influence the agent's prompts/behavior.
Audit Metadata