ClawHub
Back to skill

Security audit

Deliverability Qa

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped email deliverability checklist that reads user-provided sending evidence and only saves results to memory after asking.

Installers should be comfortable sharing email deliverability materials such as DNS/DMARC evidence, ESP reports, reputation data, seed-test results, and campaign HTML. Review any optional API-key use and approve memory saves or consent-record writes only when you want those records retained.

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 77)May include surrounding context.

md
## Save Results

After delivering, ask "Save these results for future sessions?" If yes, write the pre-flight report and the reusable SEND-`S` summary to `memory/email/deliverability-qa/YYYY-MM-DD-<domain-or-topic>.md` — see [skill-contract.md §Save Results Template](../../../references/skill-contract.md). Promote deliverability blockers and the `S` score to `memory/hot-cache.md` and add unresolved fixes to `memory/open-loops.md`. Do not write memory without asking.

## Reference Materials

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 · references/deliverability-checklist.md (reported line 40)May include surrounding context.

md
- Recent list-cleaning / bounce suppression in place.
- Re-engagement or sunset path exists for chronically unengaged addresses (this is also the SEND-`E` engagement-decay sub-item — note it, but `E` is scored elsewhere).
- Consent basis on file per subscriber (consult [consent-registry](../../../../protocol/consent-registry/SKILL.md)); **no consent record = S2 NEEDS_INPUT**, and the S2 verdict belongs to the auditor.

## Output

Static analysis

No suspicious patterns detected.