Security Audit

gatherup-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

gatherup-automation received a trust score of 95/100, 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, 1 medium, and 0 low severity. Key findings include Broad Access to Third-Party API Operations.

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 17, 2026 (commit 99e2a295). 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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Broad Access to Third-Party API Operations The skill provides the LLM with broad access to all available Gatherup operations via the `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_SEARCH_TOOLS` functions. While intended for automation, this design allows a potentially malicious prompt to instruct the LLM to discover and perform any action supported by the connected Gatherup account. This includes sensitive data manipulation, deletion, or retrieval, without granular permission controls explicitly defined or enforced within the skill's documentation. The skill encourages discovering all tools, which means the LLM can learn about and execute any operation available through the connected Rube MCP and Gatherup integration. Implement more granular access control mechanisms within the Rube MCP or Gatherup integration to restrict the scope of operations an LLM can perform. Consider allowing the skill to only expose a predefined, limited set of Gatherup operations rather than all discoverable ones. If full access is necessary, ensure robust LLM safety guardrails are in place to prevent misuse and that the user is fully aware of the broad permissions granted.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/09ef08c9d14e6b82.svg)](https://skillshield.io/report/09ef08c9d14e6b82)