Security Audit

pdf-api-io-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

pdf-api-io-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, 1 high, 0 medium, and 0 low severity. Key findings include Dynamic Tool Execution with Broad Scope.

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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Dynamic Tool Execution with Broad Scope The skill instructs the LLM to dynamically discover and execute tools from the `pdf_api_io` toolkit using `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`. The `use_case` parameter for tool discovery (`queries: [{use_case: "your specific PDF API IO task"}]`) can be influenced by untrusted user input, allowing the LLM to potentially identify and execute tools with broad permissions within the `pdf_api_io` toolkit. If the `pdf_api_io` toolkit contains tools capable of sensitive operations (e.g., file deletion, data exfiltration, arbitrary file access, or modification of documents), this pattern creates a credible exploit path for a malicious user to prompt the LLM to perform unintended or harmful actions by guiding it to discover and execute such tools. Implement stricter controls or explicit user confirmation for the execution of sensitive tools. The skill should guide the LLM to validate or sanitize user-provided `use_case` queries and tool arguments to prevent the discovery and execution of unintended operations. Consider defining a whitelist of allowed tool slugs or requiring human approval for high-risk operations.	LLM	SKILL.md:44

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/b39280f05b4cea29.svg)](https://skillshield.io/report/b39280f05b4cea29)