agentbench-eval

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 (high risk: 0.75). The skill’s runtime path ingests outsider-authored free text from the benchmark repos’ prebuilt .claudemem/ enrichment docs (and/or generated AGENTS.md/cheatsheets) that were authored by third parties in data/eval-repos/{slug}/.claudemem/, which the agent then reads into the LLM context during planning/search.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 20, 2026, 02:58 PM
Issues
1
Security Audit — snyk — agentbench-eval