Back to skill

Security audit

meta-openai-whisper

Security checks for vulnerabilities and agentic risk

Overview

This skill does not appear destructive, but it is a poor fit for its claimed Whisper purpose and includes under-scoped cross-session learner persistence.

Install only for review or experimentation unless you are comfortable with a skill that advertises Whisper capability but mainly provides meta-learning scaffolding. Before use, require a clear transcription workflow, remove packaged learned state, and constrain or disable the learner unless its persisted notes are treated strictly as untrusted data.

Vulnerability Patterns
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • 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
  • 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)

T02 · Agent Memory Poisoning

Warning
Location
scripts/learner.py:10
Finding

Unsanitized Persistent Agent-Learning Input

Content
View full analysis
1 else True rec = (sys.argv[2] if len(sys.argv) > 2 else "") print(json.dumps(record(ok, rec), ensure_ascii=False)) ``` ### Technical Analysis The script accepts arbitrary text from the second command-line argument and appends it directly to the persistent `patterns` array. It applies no schema validation, content filtering, provenance tracking, length limit, authorization check, or distinction between observations and executable agent instructions. The project documentation states that this learner state supports a cross-session `meta-evolver` loop. If a downstream agent incorporates stored patterns into prompts, policies, or behavioral rules, attacker-controlled text could be interpreted as durable instructions. This creates a memory-poisoning boundary even though the included package does not contain the downstream consumer needed to demonstrate behavioral execution. The absence of input-size limits also permits repeated calls to grow the JSON file indefinitely, potentially degrading processing or exhausting storage allocated to the skill. ### Attack Path 1. An attacker controls or influences the note supplied to `learner.py`. 2. The attacker invokes the script with content crafted as an agent instruction, for example through the second command-line argument. 3. `record()` appends that content unchanged to `patterns`. 4. The script writes the attacker-controlled entry to `scripts/l ...[truncated 979 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
scripts/learned_patterns.json:4
Finding

Prior User and Workstation Path Disclosed in Packaged State

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill markets itself as an enhanced Whisper-derived meta-skill with self-verification, reflection, orchestration, and evolution, but the observed behavior does not implement those claims and instead appears focused on local persistence/metrics. This mismatch is dangerous because operators may grant trust, autonomy, or permissions based on false expectations, enabling covert or unjustified file activity under a misleading description.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
74% confidence
Finding

The skill declares no explicit tool scope or permissions while analysis indicates file-write capability elsewhere in the skill package or its associated implementation. Undeclared write access weakens least-privilege controls and can let the skill modify local state, logs, or other files in ways reviewers and users did not consent to.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains user-facing natural-language instructions and descriptions exclusively in Chinese, with no indication that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire markdown file is written in Chinese and provides no indication that language choice is optional or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest presents this skill as an enhanced form of 'openai-whisper', which implies audio transcription-related capability. However, this file describes only capability-signature extraction, self-reflection, self-verification, integration, and cross-session self-evolution, with no indication of Whisper-style audio handling or transcription operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file’s primary natural-language description is written only in Chinese and does not indicate any user language choice or opt-in. Per the policy, forcing a specific language or locale without user choice is a natural-language policy concern.

Content

No source excerpt is available for this finding.