Security Audit

communication-coach

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

communication-coach received a trust score of 97/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.

SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 0 medium, and 1 low severity. Key findings include User communication stored locally.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

98%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
LOW	User communication stored locally The `scripts/manage_state.py` script contains functionality to save user-provided communication text to local files within the `samples/` directory (via the `--save-sample` argument). The `SKILL.md` explicitly states that `samples/` contains 'Tagged analyzed comms (not loaded, used for baseline calc)'. While this local storage is an intended feature for baseline calculations and historical tracking, it means potentially sensitive user data is persistently stored on the local filesystem. This creates a data retention and privacy risk, as this data could be accessed by unauthorized parties if the skill's execution environment is compromised, or if the LLM is later prompted to retrieve and expose these files. Inform users explicitly about the local storage of their communication data. Implement data retention policies (e.g., automatic deletion after a specified period). Consider providing options for users to opt-out of sample storage or to encrypt stored data. Ensure the skill's execution environment has appropriate access controls to protect these files.	LLM	scripts/manage_state.py:140

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/b07e18c216cdef3e.svg)](https://skillshield.io/report/b07e18c216cdef3e)