ClawHub
Back to skill

Security audit

Proof Point Packager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped marketing proof-packaging helper with disclosed project-memory reads and confirmation-gated memory writes.

Before installing, confirm you are comfortable with the skill reading your project's claims ledger, story bank, message-house files, and pasted proof material, and only approve memory saves when the packaged proof and gap proposals are accurate.

A.I.G

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

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 67)May include surrounding context.

md
## Save Results

After delivering the proof module set, ask: "Save these results for future sessions?" On confirmation, save to `memory/narrative/proof-point-packager/YYYY-MM-DD-<topic>.md` — see [skill-contract.md](../../../references/skill-contract.md) §Save Results Template. Every proof gap and every not-yet-ledgered proof goes only to `memory/events/claims.ndjson` via an authorized `operation: propose` request to `registry-events.py` marked `[needs source]`; a canon-grade proof fact (one that belongs in the durable narrative record) is proposed to `memory/events/narrative.ndjson` via an authorized `operation: propose` request to `registry-events.py` only — this skill never writes the `memory/narrative-registry/` canonical files, which [narrative-registry](../../../protocol/narrative-registry/SKILL.md) alone owns. Do not write memory without asking.

## Reference Materials

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The natural-language metadata presents the skill name and summary in a bilingual form, including Chinese text, but does not indicate that language selection is optional or user-driven. This can conflict with a policy requiring language or locale choice rather than implicitly imposing one presentation style.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.