Back to skill

Security audit

meta-boss-skills

Security checks for vulnerabilities and agentic risk

Overview

This skill needs Review because it combines broad agent-orchestration claims, sensitive workplace-material workflows, and cross-session note persistence without enough scoping or user control.

Install only if you are comfortable with a skill that may handle sensitive workplace text and retain notes across runs. Approve any generated-file workflow deliberately, avoid putting secrets or private conversations into learner notes, and treat the claimed self-evolution and orchestration features as under-scoped rather than fully implemented.

Vulnerability Patterns
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T02 · Agent Memory Poisoning

Warning
Location
scripts/learner.py:12
Finding

Unvalidated Attacker-Controlled Notes Persisted in Cross-Session Learning State

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 intended cross-session use is also documented in `SKILL.md:31-35`, including the requirement to inject results into the learner and continuously evolve behavior across sessions. ### Technical Analysis The `record()` function accepts an arbitrary `note` and appends it to `patterns` without schema validation, content filtering, size limits, provenance tracking, or separation between passive observations and executable instructions. The resulting value is persisted in `scripts/learned_patterns.json`. Because the skill explicitly advertises this file as part of a cross-session learning and evolution loop, attacker-controlled text can become durable state. If a downstream agent, prompt builder, or `meta-evolver` component later interprets stored patterns as behavioral guidance, malicious notes can influence future sessions. The present repository does not contain the downstream consumer that converts these records into agent instructions. Consequently, direct future instruction execution is conditional on the advertised external learning integration. The confirmed behavior within this package is persistent storage of arbitrary caller-supplied content. The storage ...[truncated 1629 chars]
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The declared description presents a broad, advanced meta-skill with multiple higher-order capabilities: self-verification, self-reflection, orchestration, and ongoing self-improvement. The supplied code only implements a narrow persistence utility that logs invocation outcomes and notes to a local JSON file. While this logging could support a larger meta-evolution system, the code chunk itself does not perform the advanced capabilities claimed. Therefore the description materially overstates what this code actually does.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill text explicitly instructs the agent to 'run the writer script yourself' and write output into bosses/{slug}/, which implies file-write behavior without any declared permissions or allowed-tools boundary. Undeclared write capability is dangerous because it bypasses least-privilege expectations, making it easier for the skill to create or overwrite files in ways users and platform controls may not anticipate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The listed intent signals such as 'analyze my boss' or 'help me distill my boss' are common natural-language phrases that could appear in ordinary conversation. Ambiguous trigger phrasing can cause accidental activation, leading the skill to collect source material, orchestrate follow-on behavior, or generate artifacts when the user did not intend to invoke the full skill workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The usage section says to 'directly call this skill' for the whole boss-skills domain, with no narrow trigger or activation guardrails. Overly broad activation increases the chance the skill will engage on loosely related prompts and perform higher-risk behaviors such as orchestration, reflection, or file-producing workflows without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language description and usage guidance are presented entirely in Chinese, with no indication that users may choose another language or locale. This can violate language/locale policy when a skill implicitly fixes output language without user opt-in or documented regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into a preferred language. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.