internet-skill-finder
Warn
Audited by Snyk on Jun 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text can be ingested when the skill uses the GitHub Connector /
--onlinemode to fetch repository content (e.g., README/skill descriptions from public GitHub repos) and then includes it in the agent’s LLM context for result presentation.
MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).
- Hidden Unicode characters detected (1 type(s) found)
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W021
MEDIUMHidden or invisible Unicode characters detected (potential obfuscation or prompt injection).
Audit Metadata