hackerone
Warn
Audited by Snyk on May 12, 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's SKILL.md explicitly instructs fetching HackerOne program pages and downloading public scope CSVs (Option 1) and then injects the fetched "program_guidelines" into coordinator/executor agent prompts (see the coordinator Agent(prompt=f"...SCOPE: {program_guidelines}...")), so untrusted third‑party content is read and can directly influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata