ClawHub
Back to skill

Security audit

Pitch Narrative Builder

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for building pitch narratives, but it asks for persistent memory writes that are not declared in its manifest capabilities.

Review this before installing if your host relies on the manifest for permissions. The narrative workflow itself is reasonable, but the package should either declare narrowly scoped write capabilities or return proposed records inline unless you explicitly approve each destination and payload.

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 Manifest's Declared Capability Boundary

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 pitch narrative, ask: "Save these results for future sessions?" On confirmation, write `memory/narrative/pitch-narrative-builder/YYYY-MM-DD-<topic>.md` per the [Skill Contract](../../../references/skill-contract.md) §Save Results Template. Every `[needs source]` proof goes only to `memory/events/claims.ndjson` via an authorized `operation: propose` request to `registry-events.py`; any canon-grade wording surfaced while drafting goes 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

Static analysis

No suspicious patterns detected.