Back to skill

Security audit

notion-personal-space-audit

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it may read and summarize unrelated Notion workspace content beyond the selected personal hub; the scanner review is partial, so the evidence is incomplete.

Consider the confirmed scope concern before installing: the skill could access and summarize unrelated Notion content. The scan is partial because a referenced local path was missing, so it does not establish that all behavior was reviewed.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (4)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
ports belong in a separate high-sensitivity archive; short event logs retain event records; raw conversations remain source material and link to derived decisions.
9. **[LLM]** Recommend minimal shared fields: content type, domain, status, occurrence date, organization date, sensitivity, and relations. Do not force one schema onto all content types.
10. **[LLM]** Produce a concise Markdown report with evidence, signal-light findings, proposed tree, migration table, phased migration order, and a clear statement that no Notion content was changed.
11. **[LLM]** If the user explicitly authorizes structure creation, create only empty navigation pages and usage instructions after the audit. Never move, delete, rename, or rewrite existing content unless separately authorized.
12. **[LLM]** If the user explicitly authorizes updating an existing audit/guide page, append a clearly marked usage-notes section rather than replacing prior findings; make the write idempotent with a unique marker and

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
1. Read-only by default: no Notion write endpoint is called unless the user explicitly authorizes structure creation or updating an existing guide page; authorized guide-page updates must append rather than replace.
2. Never move, delete, rename, or rewrite existing content as part of an audit or structure setup.
3. Never expose access tokens in reports, logs, or user-facing output.
4. Do not invent content the API did not return; mark inaccessible or uncertain areas explicitly.
5. Sensitive analysis reports are never classified as ordinary log events, and never merged into general archives.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

md
- Do not merge raw conversations, derived reports, and action plans into one record. Keep source, analysis, and action linked but distinct.
- Do not delete empty book/person placeholders during an audit. Put them in an archive or pending-review view first.
- Orphan pages not under any database are easy to miss; enumerate workspace top-level nodes first and recurse. Do not rely on database enumeration alone.
- Do not expose access tokens in reports, logs, or user-facing output.
- Do not modify Notion without explicit confirmation. The audit should produce a migration plan first.
- When structure creation is authorized, use idempotent title checks and create pages under the audited parent; do not move, delete, rename, or rewrite existing content as part of structure setup.
- Notion block append requests must be chunked to at most 100 blocks; use a unique marker to prevent duplicate guide sections, and verify by reading back the full child-block list rather than trusting the write respons

L063 directs workspace-wide enumeration and recursion rather than limiting discovery to the selected personal hub and its descendants.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The instruction to enumerate workspace top-level nodes and recurse is broader than the selected personal hub and its descendants. Despite the initial scope-confirmation step, this unqualified directive could cause the agent to retrieve and summarize unrelated private content accessible to the Notion integration; read-only operation prevents modification but not excessive access or disclosure.

Content

No source excerpt is available for this finding.