jeo-skill
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). At runtime,
scripts/jeo-skill.pydownloads and parses free-text JSON catalog data fromhttps://raw.githubusercontent.com/akillness/jeo-skills/main/.agent-skills/skills.json(or a local cache) viadownload_catalog()->validate_catalog()->json.loads, and that outsider-authored content is ingested without first selecting a specific item.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The CLI (scripts/jeo-skill.py) fetches the remote catalog at runtime from https://raw.githubusercontent.com/akillness/jeo-skills/main/.agent-skills/skills.json and uses it to determine which skills to list/install, and it passes the GitHub repo URL https://github.com/akillness/jeo-skills to npx which can fetch/execute remote code—so remote content controls runtime behavior and installation actions.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata