sales-greenshift
Warn
Audited by Snyk on Jul 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). SKILL.md instructs the agent to read
references/learnings.mdandreferences/platform-guide.md(and related API reference files) at runtime, which are outsider-authored public documentation excerpts (e.g., Greenshift public docs fetched/reproduced), so the LLM ingests free text originating outside the operating user’s chosen inputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata