sparta-review
Warn
Audited by Snyk on Mar 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly invokes /dogpile to perform live web research (searching Brave, Perplexity, ArXiv, MITRE, etc.) as part of Brandon's workflow—see "Brandon's Research (via /dogpile)" in SKILL.md and the run_research function in run.sh that calls PI_SKILLS/dogpile/run.sh—so it ingests untrusted public web content at runtime which can materially influence assessments and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata