memory
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's sync workflow and scripts (reference/remote-sync.md and scripts/sync-pull.sh / scripts/sync-push.sh) explicitly fetch and ingest GitHub/GitLab Issues (user-generated, third‑party content) and use them as the source of truth for agent context and actions, so untrusted issue content can materially influence the agent's decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The sync scripts (scripts/sync-pull.sh and sync-push.sh) use the repo remote (via git remote get-url origin — e.g. https://github.com/OWNER/REPO.git or git@github.com:OWNER/REPO.git) and gh/glab at runtime to fetch Issue bodies and inject them into .memory/context.md, so remote Issue content can directly influence agent prompts.
Audit Metadata