AgentScore's scanning service and free API close after 31 December 2026. If you rely on them, please get in touch before then.
AgentScore is for sale. View the assets and acquisition details →
high

AGENTSCORE-2026-0131

MCP package: clawmem

Published 9/27/2026 · 0.37.0 → 0.39.0

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.

clawmem updated from 0.37.0 to 0.39.0. Score changed 85/100 to 70/100 (-15). Risk: LOW to MODERATE. 3 findings.

85 → 70
Score
LOW → MODERATE
Risk
WARN
Verdict

Findings

  • low unsafe_eval: Uses eval() with dynamic input (downgraded — mitigators detected in scope: documentation_context:``` , documentation_context:# C)
  • high command_injection: Potential command injection: shell execution with template literal input
  • low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: yoloshii