session-management
Warn
Audited by Snyk on Feb 23, 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 workflow explicitly supports PR-linked sessions (e.g., "claude --from-pr https://github.com/org/repo/pull/156" in SKILL.md), which indicates the agent will fetch and use user-generated GitHub PR content as runtime context and thus could ingest untrusted third‑party content that influences its actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill shows runtime use of a GitHub PR URL (e.g., "claude --from-pr https://github.com/org/repo/pull/156"), which implies the agent will fetch PR content at runtime and inject that external text into the session context—directly influencing prompts/instructions.
Audit Metadata