skillhone-evaluation
Warn
Audited by Snyk on Jul 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). Trajectory-analyzer reads
workdir/work_<uid>/trajectory.jsonl(solver logs that can include outsider-authored free text from tool outputs/user messages) and then feeds extracted error strings into the agent’s LLM context during analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata