Security Audit
tapfiliate-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
tapfiliate-automation received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned Rube MCP dependency, Skill enables broad execution of external tools.
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 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unpinned Rube MCP dependency The skill's manifest specifies a dependency on 'rube' for the 'mcp' requirement but does not pin it to a specific version. This means that any version of the 'rube' MCP could be used, potentially introducing breaking changes, vulnerabilities, or malicious code if the 'rube' project or its distribution mechanism were compromised. Relying on unpinned dependencies increases supply chain risk. Pin the 'rube' dependency to a specific, known-good version (e.g., `{"requires": {"mcp": ["rube==1.2.3"]}}`) in the manifest to ensure consistent and secure behavior. | LLM | SKILL.md | |
| MEDIUM | Skill enables broad execution of external tools The skill's core workflow pattern involves dynamically discovering tools via `RUBE_SEARCH_TOOLS` and then executing any discovered tool via `RUBE_MULTI_EXECUTE_TOOL` using `tool_slug: "TOOL_SLUG_FROM_SEARCH"`. This design allows the AI agent to perform a wide range of operations on the connected Tapfiliate account, depending on the capabilities exposed by the underlying Tapfiliate toolkit. While flexible, this broad execution scope means that if the AI agent is compromised or manipulated (e.g., via prompt injection), it could be directed to perform highly sensitive or destructive actions on the Tapfiliate platform without specific constraints defined within the skill itself. Implement stricter controls or allow-lists for tool execution where possible, especially for sensitive operations. Consider adding a layer of human approval or explicit confirmation for high-impact actions. Ensure the LLM using this skill is robustly protected against prompt injection to prevent misuse of this broad capability. | LLM | SKILL.md:50 |
Scan History
Embed Code
[](https://skillshield.io/report/c1f88319eac5bfe7)
Powered by SkillShield