ecl-harness-engineer
Warn
Audited by Snyk on Jun 26, 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). The skill’s runtime LLM context can include outsider-authored free text from the target repository itself—e.g., it reads
README.md,docs/STATUS.md, and especially archivedharness/changes/**/summary.md/spec.md/plan.md/tasks.md/reviews/**(outsider-authored by prior contributors) to drive context loading and handoff, which is then fed into the agent’s LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata