Security Audit
forcemanager-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
forcemanager-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 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Skill encourages dynamic, broad tool access.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Skill encourages dynamic, broad tool access The skill's core workflow pattern explicitly instructs the LLM to use `RUBE_SEARCH_TOOLS` to discover 'Forcemanager operations' and then execute them via `RUBE_MULTI_EXECUTE_TOOL`. This design allows the LLM to dynamically access and execute any tool provided by the `forcemanager` toolkit via Rube MCP, without explicit constraints on the types of operations. If the underlying `forcemanager` toolkit has highly sensitive or destructive capabilities (e.g., deleting data, modifying critical records), this broad access could be exploited by a malicious prompt to perform unintended actions. The skill itself does not define or enforce a limited scope of operations, relying entirely on the capabilities exposed by the underlying toolkit. Implement stricter access control or scope definition within the skill or the underlying Rube MCP configuration. For example, define a whitelist of allowed tool slugs or categories of operations that the LLM is permitted to discover and execute, rather than allowing arbitrary discovery and execution. The skill could also be designed to only expose a curated subset of Forcemanager tools. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/62d0c2fddf16d1e6)
Powered by SkillShield