Security audit

Teamgram MTProto Protocol

Security checks for vulnerabilities and agentic risk

Overview

This is a reference-only documentation skill with no executable behavior, though it includes Telegram-compatible app identifier constants that users should not blindly reuse for deployments.

Before installing, treat this as developer reference material only. If you operate a compatible server or client, provision your own application identity/configuration instead of relying on the published constants, and do not treat the included values as authorization or user-session credentials.

A.I.G

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 (1)

T09 · Insecure Skill Coding Practices

Note

Location: SKILL.md:82
Finding: Hardcoded Telegram Application Identifier and Hash
Content: View full analysis
Remediation: View remediation
` - `BuildVars.APP_HASH = ""` ``` 2. Instruct operators to provision and use an application identity authorized for their own deployment rather than reusing a shared identity. 3. Store the application hash outside source-controlled documentation and code, such as in an environment variable or access-controlled configuration file. 4. Avoid logging the application hash or including it in examples, generated diagnostics, or deployment artifacts. 5. If the published value is active and controlled by the project, assess its usage and rotate or revoke it where the relevant platform supports doing so. 6. Clarify that application credentials do not replace user authentication and must not be treated as authorization for access to user accounts or server administration. ]]>

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.