Back to skill

Security audit

AI Chat Export to Markdown

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence, citing risks around bearer-token handling and sensitive data masking, while noting that much of the code was only partially inspected.

Consider avoiding installation until the token handling and masking concerns are addressed and the partially inspected files receive a complete review. If you do install, review the data the skill may save or display, and use a reviewed, pinned version of any referenced CLI.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/bulk.mjs
Finding

Diagnostic probing can forward the current site's bearer token to an untrusted resource origin

Content
View full analysis

Impact

The external endpoint receives the bearer token. If that token authorizes account API access, its operator can impersonate the account within the token's scope and lifetime.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (62)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

md
- only when you run `bulk.mjs` or `biji-notes.mjs`: conversations and voice notes belonging to the account **you** are already signed in to, through that browse

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 112)May include surrounding context.

md
node scripts/biji-notes.mjs list --since 2026-11-01 [--type class_audio]

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 113)May include surrounding context.

md
node scripts/biji-notes.mjs export --since 2026-11-11 --until 2026-11-12 --out DIR --transcript

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 124)May include surrounding context.

md
、内网 IP。公网 IP 和 commit hash 不动,这些通常是有意义的信息。`read.mjs`、`sessions.mjs`、`bulk.mjs`、`biji-notes.mjs` 都走同一条路径(`lib/redact.mjs`),vendor 通道产出的是别人拼好的 markdown,落盘后就地再过一遍。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.

md
| 得到笔记 | 接口 | localStorage 的 `token`(360 字符 JWT),走 Bearer | 独立脚本 `biji-notes.mjs`,不并进 `bulk.mjs`,原因见下 |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 185)May include surrounding context.

md
走 `scripts/biji-notes.mjs`,和分享链接那条链路的接口不是一套(分享走免认证 `/share/<id>`,这里走登录态 `/notes/*`)。`--since` / `--until` 收 `YYYY-MM-DD`,`--type class_audio` 只取课堂与会议类录音,`--tran

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

md
- only when you run `bulk.mjs` or `biji-notes.mjs`: conversations and voice notes belonging to the account **you** are already signed in to, through that browse

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
The one deliberate exception: `bulk.mjs` goes through opencli to reuse the session you are already signed in to, which is the only way to read your own history

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 124)May include surrounding context.

md
JWT、Bearer)、内网 IP。公网 IP 和 commit hash 不动,这些通常是有意义的信息。`read.mjs`、`sessions.mjs`、`bulk.mjs`、`biji-notes.mjs` 都走同一条路径(`lib/redact.mjs`),vendor 通道产出的是别人拼好的 markdown

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 168)May include surrounding context.

md
`read.mjs` 一次只处理一条分享链接,`bulk.mjs` 处理你自己账号下的全部历史。区别在接口:分享走免认证的 `/share/<id>`,批量走登录后才放行的列表与详情接口。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.

md
| 得到笔记 | 接口 | localStorage 的 `token`(360 字符 JWT),走 Bearer | 独立脚本 `biji-notes.mjs`,不并进 `bulk.mjs`,原因见下 |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 198)May include surrounding context.

md
or: Failed to fetch`,iframe 与 XHR 都一样死。只从页面取一次 token,之后请求走 Node 侧 curl。这也是它没并进 `bulk.mjs` 的原因,那边全是页面内脚本。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

md
CSR_LANG=en node scripts/sessions.mjs list --limit 5

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 105)May include surrounding context.

md
node scripts/sessions.mjs list [--source claude|codex|workbuddy|all] [--limit 20] [--cwd 子串]