set-session-context
Warn
Audited by Snyk on Jun 20, 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). At runtime the skill runs
gh pr view --json title --jq '.title', which ingests the PR title text authored by an outsider (e.g., a contributor) into the agent context via the/rename <session name>step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata