other
Note
- Location
SKILL.md:36- Finding
Mandatory Undocumented Request Attribution Parameter
- Content
View full analysis
- Remediation
View remediation
Security audit
ComPDF Documents to PDF
Security checks for vulnerabilities and agentic risk
Overview
The skill has a legitimate PDF-conversion purpose, but it stores a reusable API key in a plaintext skill-local file and bundles broad ComPDF API documentation beyond conversion.
Install only if you are comfortable sending selected documents to ComPDF for processing and storing a ComPDF API key in a local plaintext api_key file beside the skill. Keep the key low-privilege if the service supports it, avoid sensitive or regulated documents unless ComPDF's terms and retention fit your needs, and do not use this skill for non-conversion endpoints despite the bundled reference material.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)
T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:38- Finding
API Credential Stored in a Plaintext Skill-Local File Without Required Filesystem Protections
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 3. Read the matching heading in `references/official-api-reference.md`. Use its exact endpoint path, request fields, request mode, and response fields; do not i
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 6. Resolve credentials only from `api_key` in the directory containing this `SKILL.md`. Read its first non-empty line. Do not inspect environment variables or a
Description-Behavior Mismatch
High
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The reference file exposes a very large API surface that goes far beyond the skill’s stated purpose of converting documents and images to PDF, including PDF decryption, watermark removal, document comparison, AI extraction, and other unrelated operations. In an agent setting, broad in-scope documentation can steer tool use outside intended boundaries, enabling unauthorized data extraction, destructive modification, or policy bypass if the agent infers those capabilities are available.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The reference index exposes and normalizes many API capabilities that materially exceed the skill’s declared purpose of converting documents and images into PDF, including PDF decryption, document extraction, webhooks, task listing, asset info, and AI parsing/extraction. In an agent setting, this kind of overbroad documentation can enable scope creep or prompt-driven misuse, causing the skill to invoke unintended endpoints with access to sensitive documents or broader account resources.
- Content
Context-Inappropriate Capability
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The reference highlights PDF security and modification features such as encryption, decryption, watermark changes, merge/split, and other manipulations unrelated to plain conversion to PDF. In context, this creates capability confusion and increases the chance an agent performs sensitive or destructive document operations that the user neither requested nor expected.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The document extensively describes direct upload, async upload, presigned upload, polling, and result download flows to a third-party service, but does not pair that with a clear user-facing warning that document contents are transmitted off-platform. For a business-document skill, that omission can lead to inadvertent disclosure of confidential, regulated, or proprietary information.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The markdown exposes a 'Delete pages' capability that removes specified pages from PDFs, but it does not provide any caution that this is a destructive content-changing operation or recommend preserving the original file. For markdown files, omission of warnings about behaviors affecting user data or system integrity is in scope.
- Content
Context-Inappropriate Capability
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
Including AI document parsing and extraction documentation in a simple document-to-PDF skill unnecessarily exposes capabilities for structured content extraction from uploaded files. This expands the risk from format conversion to sensitive data mining, which is especially dangerous because users may provide confidential business documents expecting only fixed-layout conversion.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This file is presented as an English API reference but includes multiple untranslated Chinese lines, which imposes a language requirement on readers without opt-in or explanation. The same pattern appears in several other sections, making the documentation inconsistent with a language/locale choice policy.
- Content