Back to skill

Security audit

AI Forum API

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent forum-publishing API client, but it requests far more agent authority than its purpose needs and handles the forum token in an unsafe CLI pattern.

Review this skill before installing. It appears intended to publish to AI Forum, but it should be restricted to the minimum tools needed, avoid passing tokens on the command line, and pin dependencies. Only use it with a token you can rotate or revoke, and confirm any content before publishing under your account.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (3)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:6
Finding

Excessive Agent Tool Permissions Violate Least Privilege

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
publish.py:69
Finding

Forum Token Exposed Through Command-Line Arguments

Content
View full analysis
<content_file> [category]") sys.exit(1) token = sys.argv[1] title = sys.argv[2] content_path = sys.argv[3] ``` The documented invocation also exposes the token directly: ```bash python publish.py <token> "Article title" content.md "AI Observation" ``` ### Technical Analysis The CLI requires the authentication token to be supplied as a command-line argument. Command-line arguments are not an appropriate secret transport mechanism because they can be captured by shell history, process-inspection utilities, monitoring agents, diagnostic tooling, audit logs, terminal session recording, or wrapper scripts. The implementation does not print the token directly, and the API endpoint is fixed to HTTPS. Nevertheless, exposing the token through process metadata creates a separate local disclosure path before the token is transmitted to the intended service. ### Attack Path 1. A user follows the documented CLI syntax and places the forum token directly in the command line. 2. The shell may save the complete command, including the token, in its history file. 3. While the process is running, another authorized local account, monitoring process, or administrative utility may inspect the process arguments. 4. Logging, automation, or terminal-recording systems may retain the invocation after execution. 5. An attacker with access to one of these records retrieves the token. 6. The attacker uses the token to submit requests to the forum API as the victim. ### Impact Assessment A disclosed token may allow unauthorized use of the associated forum account within the privileges granted by that token. Based on the implemented AP ...[truncated 481 chars]
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
requirements.txt:1
Finding

Dependency Version Is Not Reproducibly Pinned

Content
View full analysis
=2.28.0 ``` ### Technical Analysis The dependency declaration permits installation of any `requests` release from version 2.28.0 onward. It does not specify an upper bound, lock a reviewed transitive dependency graph, or provide package hashes. This configuration makes installations non-reproducible. A later installation can receive code different from the version used during review. Because `requests` executes in the same Python process and directly handles the token and published content, a compromised dependency source or malicious future package release would have access to those values and to the process's local permissions. The declaration does not demonstrate that the current `requests` package is malicious. The finding concerns supply-chain exposure and the absence of integrity controls. ### Attack Path 1. The project is installed at a later date using `pip install -r requirements.txt`. 2. Package resolution selects a newer release than the one originally reviewed, or retrieves a package from an untrusted or compromised index configuration. 3. The selected package or one of its transitive dependencies contains malicious code. 4. Python imports that code when `publish.py` imports or uses `requests`. 5. The malicious dependency executes with the privileges of the Skill process and can access authentication tokens, article content, environment variables, or readable local files. 6. The data may be altered, abused, or transmitted to an attacker-controlled destination. ### Impact Assessment The dependency executes inside the Skill process and therefore inherits its local operating-system permissions. A compromised dependency could potentially: - Read the forum token and submitted content. - Manipulate API requests or responses. - Access environme ...[truncated 284 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This README presents all usage and safety instructions only in Chinese, which imposes a specific language on users without opt-in. The policy allows locale constraints only when the restriction is explicitly justified or when users are offered a language choice, neither of which is present here.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code sends the user's token and supplied content to a remote API via POST requests, which is a safety-relevant network transmission of user and credential data. While the methods have brief docstrings, they do not disclose to the user that the token is attached to every request and that article/question content is sent to an external service.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The natural-language documentation in the module is entirely in Chinese and does not offer any language choice or indicate that the skill is intentionally region- or locale-specific. Under the stated policy, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
93% confidence
Finding

The dependency is specified as requests>=2.28.0, which allows any future version and does not guarantee a reproducible or reviewed install. This increases supply-chain risk and makes it harder to ensure the deployed version is free from known security issues or breaking changes.

Content

Scanner excerpt · requirements.txt (reported line 1)May include surrounding context.

text
requests>=2.28.0

Unverifiable Dependency: requests has 16 known advisory(ies) (CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
90% confidence
Finding

Because requests is not pinned, it is impossible to verify from this manifest whether the installed version is affected by any of the known advisories associated with the package. The issue is primarily uncertainty and lack of provenance: deployments may resolve to vulnerable versions depending on environment and install time.

Content

No source excerpt is available for this finding.