harness-issues
Warn
Audited by Snyk on Jun 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). At runtime, the skill’s required workflow can fetch an outsider-authored issue body/comments from the GitHub issue tracker when the user passes an issue reference (e.g.,
/harness-issues #Nor a URL/path), and then reads that full text into the agent’s conversation context.
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