hallmark
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow can fetch arbitrary brand homepages and same-origin CSS for named brands (brand-truth.md step 2) and, under signal 8, consumes text returned by an Inspo MCP archive (titles, alt text, CSS comments); the agent must actively fetch these, so outsider text is exposed only on selection, not by forced delivery.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill's
install-hook.mjspersistently wires a PostToolUse hook into the agent's environment, an operational change, but no supplied text establishes irreversible loss of operational state, so the tier is low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata