Security audit

Steam Community Inventory

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple Steam inventory helper, but it asks users to extract and export a live Steam session cookie without adequately warning or scoping that credential use.

Install only if you are comfortable giving the skill access to an authenticated Steam web session. Prefer public, unauthenticated inventory requests when possible; if you use STEAM_COOKIES, treat steamLoginSecure like a password, avoid pasting it into shared logs or terminals, unset it after use, and sign out/revoke sessions if it may have been exposed.

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

Warning

Location: SKILL.md:20
Finding: Steam Session Cookie Unnecessarily Required and Exposed Through Command-Line Arguments
Content: View full analysis
Application tab > Cookies > `https://steamcommunity.com` - Copy the value of the `steamLoginSecure` cookie 3. Set environment variables: ```bash export STEAM_ID="your-steamid64" export STEAM_COOKIES="steamLoginSecure=your-cookie-value" ``` ``` The credential is subsequently expanded into `curl` command-line arguments: ```bash curl -s "https://steamcommunity.com/inventory/$STEAM_ID/$APP_ID/2?l=english&count=2000" \ -H "Cookie: $STEAM_COOKIES" | jq '.' ``` The same pattern is repeated for CS2 inventory retrieval, item summaries, item details, and paginated requests: ```bash curl -s "https://steamcommunity.com/inventory/$STEAM_ID/730/2?l=english&count=2000" \ -H "Cookie: $STEAM_COOKIES" | jq '.' curl -s "https://steamcommunity.com/inventory/$STEAM_ID/730/2?l=english&count=2000" \ -H "Cookie: $STEAM_COOKIES" | jq '[.descriptions[] | {market_hash_name, type}]' curl -s "https://steamcommunity.com/inventory/$STEAM_ID/730/2?l=english&count=2000" \ -H "Cookie: $STEAM_COOKIES" | jq '{assets: [.assets[] | {assetid, classid, instanceid, amount}], total: .total_inventory_count}' curl -s "https://steamcommunity.com/inventory/$STEAM_ID/730/2?l=english&count=2000&start_assetid=$LAST_ASSET_ID" \ -H "Cookie: $STEAM_COOKIES" | jq '.' ``` ### Technical Analysis The Skill instructs users to manually extract the sensitive `steamLoginSecure` authentication cookie and supply it to every inventory request. Shell expansion of `$STEAM_COOKIES` places the credential in the argument list passed to `curl` ...[truncated 2525 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly instructs the user to extract a live Steam session cookie (steamLoginSecure) from browser developer tools and store it in an environment variable, but it does not warn that this cookie is effectively an authentication credential. If exposed through shell history, logs, process listings, or downstream tooling, an attacker could reuse the session to access the user's Steam account context and inventory-related actions permitted by that session.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 98% confidence
Finding: Multiple example requests include the query parameter l=english, which forces English-language responses. This is a natural-language locale constraint and the document does not provide an opt-in, alternative locale guidance, or a justification for requiring English.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.