ClawHub
Back to skill

Security audit

Narrative Resonance Monitor

Security checks for vulnerabilities and agentic risk

Overview

The skill's main workflow is understandable, but its package metadata understates the network/script and memory-write actions it tells an agent to perform.

Install only in a host that enforces per-operation permissions. Allow the named connectors and memory paths only if you expect this skill to perform resonance monitoring, and require confirmation before report saves, event proposals, open-loop updates, or cache changes.

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
distribution-manifest.json:2
Finding

Skill Operations Exceed the Capabilities Declared in the Distribution Manifest

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 (1)

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 report, ask: "Save these results for future sessions?" On confirmation, write `memory/narrative/narrative-resonance-monitor/YYYY-MM-DD-<topic>.md` per the [skill-contract.md](../../../references/skill-contract.md) §Save Results Template. Unbacked resonance/effectiveness statements go only to `memory/events/claims.ndjson` via an authorized `operation: propose` request to `registry-events.py`. This skill writes no canonical `memory/narrative-registry/` files — only [narrative-registry](../../../protocol/narrative-registry/SKILL.md) does; if a resonance read surfaces a canon-grade lexicon or naming fact, submit it to `memory/events/narrative.ndjson` via an authorized `operation: propose` request to `registry-events.py` only. Do not write memory without asking.

## Reference Materials

Static analysis

No suspicious patterns detected.