Back to skill

Security audit

meta-adversarial-robustness

Security checks for vulnerabilities and agentic risk

Overview

This skill is not overtly malicious, but it asks for persistent learning and self-modification authority that is broader and less controlled than a robustness-testing helper needs.

Review this skill carefully before installing. It should be limited to explicit, user-approved writes to learned_patterns.json, and any proposed changes to SKILL.md should be generated as a reviewed patch rather than applied automatically. Avoid feeding it sensitive prompts or private evaluation details until memory retention, deletion, and trust-labeling behavior are clarified.

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

Unvalidated Attacker-Controlled Data Is Written to Persistent Agent Memory

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
scripts/learner.py:18
Finding

Documented Learner Commands Are Silently Misinterpreted by the CLI

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)) ``` The documented interface in `SKILL.md:55-67` presents named operations including `record`, `prefer`, `insight`, and `reflect`, together with flags such as `--capability`, `--fail`, `--error`, `--note`, `--key`, and `--val`. None of those subcommands or flags are parsed by the implementation. ### Technical Analysis The program treats every first argument other than the literal value `fail` as a successful operation. It treats only the second positional argument as the note and silently ignores all remaining arguments. For example, when a documented command begins with `record` and then supplies the skill directory, the implementation treats `record` as a successful outcome and persists the directory argument as a pattern. Commands named `prefer`, `insight`, and `reflect` do not perform their documented functions; they merely update the operation counter and may store the next positional argument. Unknown operations and flags are not rejected. This causes persistent state to diverge from user intent and creates false confidence that reflection, preference management, or insight generation occurred. ### Attack Path 1. A user or automated agent invokes one of the commands documented in `SKILL.md`. 2. The script does not recognize the documented subcommand or parse its options. 3. The first argument is interpreted only as success unless it equals `fail`. 4. The second argument, which may be a path or unrelated option value, is stored as a persistent pattern. 5. Remaining arguments are discarded without warning. 6. Later decisions may rely on corru ...[truncated 662 chars]
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The description claims a broad, advanced meta-skill with capabilities such as self-verification, self-reflection, orchestration, and iterative self-improvement beyond a teacher skill. The provided code does not implement those behaviors. It only reads and writes a local JSON file to record invocation counts, failure counts, and notes. While this could be a supporting component for a larger meta-evolution loop, the supplied chunk’s actual primary purpose is persistent logging/record-keeping, which is materially narrower than the declared skill behavior.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill documents behaviors that imply file-writing and persistent state changes, but it declares no explicit tool scope or permissions boundary. This creates a capability-transparency problem: a caller may invoke the skill without realizing it can write memory files or potentially modify artifacts, increasing the risk of unauthorized persistence or state tampering.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language content of the skill, including its description and operating instructions, is presented in Chinese only. This effectively forces a specific language without user opt-in or any explanation that the skill is intended for a Chinese-only audience.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill stores user preferences, evaluation history, and accumulated patterns across sessions even though that persistence is not clearly necessary for a robustness-analysis function. Cross-session memory can expose sensitive operational data, create profiling risk, and be reused in later contexts without the user's informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill describes automatic persistence of evaluation history and user preferences without an explicit privacy notice, consent flow, or retention policy. That can lead to covert data retention of potentially sensitive prompts, decisions, and operator habits, which is especially risky in multi-user or shared environments.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly contemplates writing back to its own SKILL.md as part of self-evolution, which crosses from analysis into self-modification. Self-modifying agent artifacts are dangerous because they can silently expand behavior, bypass review, and persist unsafe or poisoned instructions across future runs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module docstring is written as a fixed Chinese-language description, indicating a locale-specific presentation without offering user choice or explaining a region-specific requirement. This can violate language/locale policy when the skill is used in broader contexts.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

These lines describe connecting the skill into a broader 'perception→planning→execution→verification→reflection→memory' super-agent loop and continuous meta-evolution across sessions. That is broader than merely providing adversarial-robustness capability with better verification, and introduces orchestration/platform behavior not evident from the core purpose of the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document is entirely written in Chinese, including headings and operational descriptions, with no indication that language selection is optional or user-configurable. Under the policy, a skill artifact that enforces a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This Python code writes persistent data to learned_patterns.json, which affects local user/system state. While the module docstring describes recording invocation outcomes, there is no confirmation prompt, user-facing log/print before the write, or inline warning near the operation itself.

Content

No source excerpt is available for this finding.