ClawHub
Back to skill

Security audit

Narrative Enablement Kit

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it says, but it asks to write persistent narrative and claim records even though its manifest advertises read-only style capabilities.

Install only if you are comfortable with this skill proposing or saving narrative and claim material into your workspace memory. Prefer a version whose manifest declares the needed write capabilities and that asks before each persistent claim or narrative event write.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:41
Finding

Persistent-State Writes Exceed the Declared Package Capabilities

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
## Save Results

After delivering the kit, ask: "Save these results for future sessions?" On confirmation, write `memory/narrative/narrative-enablement-kit/YYYY-MM-DD-<topic>.md` per the [skill-contract.md](../../../references/skill-contract.md) §Save Results Template. Claim wording goes only to `memory/events/claims.ndjson` via an authorized `operation: propose` request to `registry-events.py`; canon-grade facts (a boilerplate or positioning statement the user wants to make durable) go only to `memory/events/narrative.ndjson` via an authorized `operation: propose` request to `registry-events.py` — [narrative-registry](../../../protocol/narrative-registry/SKILL.md) is the sole writer of `memory/narrative-registry/` canonical files. Do not write memory without asking.

## Reference Materials

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The display name, summary, and description include mandatory bilingual Chinese text rather than presenting language as a user choice. Under the language/locale policy rule, forcing a specific language or locale without opt-in can be a policy violation unless clearly justified as region-specific, which is not documented here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.