Back to skill

Security audit

investor-update

Security checks for vulnerabilities and agentic risk

Overview

This skill drafts investor-update emails from user-approved materials and connected session sources, with clear no-send and review-before-sending limits.

Before installing, users should only connect or point the skill at Slack channels, email threads, and analytics or billing sources they are comfortable using for an investor update, because the draft may include sensitive revenue, burn, runway, customer, hiring, and fundraising information.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README claims the skill 'does not connect to any source,' but later says it pulls material from Slack, Gmail, and analytics/billing MCPs reachable in the session. This mismatch can mislead operators and users about the skill's actual data access behavior, increasing the risk of unintentionally exposing sensitive communications, financial data, or investor-related information to the drafting workflow.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 17)May include surrounding context.

md
## How to install

**Claude Code / Agent SDK:** drop the `investor-update/` folder into your skills directory (e.g. `~/.claude/skills/`). It loads automatically and triggers on investor-update requests.

**claude.ai / manual use:** open `SKILL.md`, copy it into a Project's instructions, and start a chat with "draft my investor update."

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README says the skill 'triggers on investor-update requests' and gives 'draft my investor update' as an example, but it does not define a specific activation phrase or clear boundaries for when invocation should or should not occur. This ambiguity could cause unintended activation from ordinary conversational requests about investor communications.

Content

No source excerpt is available for this finding.