AGENTSCORE-2026-0115
MCP package: @mrrlin-dev/external-agents
Published 9/1/2026 · 0.47.0 → 0.59.0
Automated, not yet reviewed
This advisory was generated automatically by a pattern-matching scanner when the package's score changed. Its findings have not been checked in the package source yet. Pattern matching produces false positives: when automated command-injection findings were first reviewed in source, most were not exploitable. Treat unreviewed findings as leads, not verdicts.
@mrrlin-dev/external-agents updated from 0.47.0 to 0.59.0. Score changed 85/100 to 75/100 (-10). Risk: LOW to MODERATE. 4 findings.
85 → 75
Score
LOW → MODERATE
Risk
ALLOW
Verdict
Findings
- low install_script: Package has 'postinstall' script: node scripts/postinstall-banner.mjs || true
- low command_injection: Potential command injection: shell execution with template literal input (downgraded — mitigators detected in scope: sanitizer:spawn(process.execPath, [, sanitizer:path.join)
- medium hardcoded_secret: Hardcoded secret found (AWS key, OpenAI key, GitHub token, or npm token) (downgraded — mitigators detected in scope: test_fixture:test(, test_fixture:abcdef)
- low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: aiuxsolutions