Back to skill

Security audit

Industry Opportunity Radar / 行业机会雷达

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent with its JishuDB-based research purpose, but it warrants Review because its bundled setup can install and launch desktop software and the Windows helper invokes PowerShell despite documentation saying it should not.

Install only if you intend to use JishuDB for this workflow and trust the publisher to install and launch JishuDB Desktop, edit MCP client configuration, use OAuth/client trust, and persist research records. Review the Windows setup path carefully because the executable helper uses PowerShell even though the documentation says it should not.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
Findings (32)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

On Windows, the skill instructions include downloading executables, manipulating LOCALAPPDATA and temp contents, inspecting/modifying ACL-related state, executing installers and PowerShell, and configuring local endpoint metadata, none of which are disclosed by the research-oriented description. That gap can mislead users and policy engines into granting broad execution rights to what appears to be a content-analysis skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

On Windows, the skill instructions include downloading executables, manipulating LOCALAPPDATA and temp contents, inspecting/modifying ACL-related state, executing installers and PowerShell, and configuring local endpoint metadata, none of which are disclosed by the research-oriented description. That gap can mislead users and policy engines into granting broad execution rights to what appears to be a content-analysis skill.

Content

No source excerpt is available for this finding.

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 307)May include surrounding context.

md
content; replay URL/preparation only with identical supported keys and
   arguments. After repair and reconciliation within the authorized scope, use
   `kb_retry_job({kbId, jobId})` for an existing failed/cancelled job. Never
   rotate identities, repeatedly import, delete history, or poll endlessly.
   Retain sanitized errors and non-secret recovery IDs.

### Recurrence is separate host automation

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 1190)May include surrounding context.

sh
assert_digest "$partial_path" "$expected_sha" installer
    cnb_revalidate_approval
    /bin/mv -- "$partial_path" "$installer_path"
    /bin/rm -f -- "${root}/download-location.txt"
  fi
  jxa result download "$PLAN_PATH" "$PLAN_SHA256" "$offset" "$added"
}

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The script invokes native Windows tools and subprocesses such as whoami, icacls, explorer, PowerShell, and the downloaded installer, while also manipulating filesystem permissions and launch behavior. Even though the code includes validation and hardening, these are still powerful system-administration primitives that are unjustified in the context of an industry-analysis skill and expand the blast radius to arbitrary host changes or software execution.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

This file is a full Windows installer/downloader/executor that writes files, changes ACLs, launches installers, creates shortcuts, and starts desktop applications. That behavior is materially unrelated to the skill’s stated purpose of tracking industry changes and comparing evidence snapshots in JishuDB, so it creates an unexpected software-deployment capability that could be abused to modify the host under the guise of an analytics skill.

Content

No source excerpt is available for this finding.

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · references/jishudb-setup/setup.md (reported line 1)May include surrounding context.

md
<!-- Generated by scripts/bundle-task-setup.py; edit skills/jishudb instead. -->

This setup guide and its helpers are included in the current task Skill.
No separate Skill installation or marketplace download is needed. Resolve

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

This file is a full JishuDB installation and authorization runbook, which is materially unrelated to the stated purpose of the skill: tracking industry changes and comparing research evidence snapshots. That mismatch is dangerous because it can cause an agent invoked for a business-analysis task to perform privileged environment changes, client registration, OAuth/token setup, and software installation outside user expectations.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The file grants broad capabilities to install software, modify client configuration, launch OAuth flows, and prepare runtime state, none of which are justified by the manifest's industry-opportunity use case. In context, these instructions expand the operational authority of a content-analysis skill into host mutation and authentication actions, increasing the chance of privilege abuse, unintended persistence, or deceptive user consent.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill orchestrates powerful operations such as network access, local setup, file writes, process execution, and configuration changes, yet it declares no explicit tool scope or permission boundaries. In a hostile or overly permissive host, this creates confused-deputy risk because the agent may invoke sensitive capabilities without clear least-privilege constraints or user-visible approval semantics.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% 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 63)May include surrounding context.

md
after the user acts, verify completion and continue automatically. Ask again
   only for uncovered material changes or genuinely missing authorization.
   Follow the setup guide's expiry and failure rules; never alter signed plans,
   bypass consent or repeatedly execute an installer with an unknown outcome.

5. Begin research, source transfer, or deliverable generation only after a real
   host capability call, required runtime readiness, and the task's destination

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions specify "the user's language, mainland China as a starting geography" as a default behavior. This imposes a locale/geography assumption unless the user overrides it, which can violate language/locale policy expectations when no opt-in or justification is provided.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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/jishudb-setup/references/connection-recovery.md (reported line 45)May include surrounding context.

md
| Observation | Check and recovery |
| --- | --- |
| No host entry or wrong effective entry | Locate the configuration actually loaded by the client. Resolve overlapping scopes or overrides before editing. Offer a target choice if unresolved. |
| File contains JishuDB but the host's MCP list does not | This is an unloaded configuration, not yet an OAuth failure. Use the host's supported reload/refresh or configuration-save action and read its list back. If no such action is exposed, return `USER_ACTION_REQUIRED` for a safe user-operated reload/import or restart. Do not ask the user to trust an entry that has not appeared. |
| DNS failure, no route, or connection timeout | Verify the selected host and service reachability from the client. Ask for an updated address or restoration of the required network only when needed. A private IP or timeout does not prove a VPN or subnet cause. |
| Local connection refused | Resolve `desktop-endpoint.json`; check the installed app and listener. Start the existing app within the authorized scope and current user's desktop session. An SSH service-session process is not proof of a working desktop launch. |
| App uninstalled; endpoint or data-location JSON remains | Preserve the files. The endpoint is a port preference; the data bootstrap locates retained data. Use the installation helper's reviewed plan: valid retained data selects an interactive data-preserving reinstall, while an endpoint alone can be reused by a fresh install. Do not delete data or configuration to satisfy fresh-install checks. |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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/jishudb-setup/setup.md (reported line 335)May include surrounding context.

md
| Observation | Check and recovery |
| --- | --- |
| No host entry or wrong effective entry | Locate the configuration actually loaded by the client. Resolve overlapping scopes or overrides before editing. Offer a target choice if unresolved. |
| File contains JishuDB but the host's MCP list does not | This is an unloaded configuration, not yet an OAuth failure. Use the host's supported reload/refresh or configuration-save action and read its list back. If no such action is exposed, return `USER_ACTION_REQUIRED` for a safe user-operated reload/import or restart. Do not ask the user to trust an entry that has not appeared. |
| DNS failure, no route, or connection timeout | Verify the selected host and service reachability from the client. Ask for an updated address or restoration of the required network only when needed. A private IP or timeout does not prove a VPN or subnet cause. |
| Local connection refused | Resolve `desktop-endpoint.json`; check the installed app and listener. Start the existing app within the authorized scope and current user's desktop session. An SSH service-session process is not proof of a working desktop launch. |
| App uninstalled; endpoint or data-location JSON remains | Preserve the files. The endpoint is a port preference; the data bootstrap locates retained data. Use the installation helper's reviewed plan: valid retained data selects an interactive data-preserving reinstall, while an endpoint alone can be reused by a fresh install. Do not delete data or configuration to satisfy fresh-install checks. |

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/jishudb-setup/references/setup-quickstart.md (reported line 105)May include surrounding context.

md
2. Read `/api/service/capabilities` from that verified endpoint without
   credentials or redirects. For `agentOnboarding.schemaVersion=1`,
   `supported=true` and `route=initial-consent` or `owner-consent`, use native
   OAuth without asking for a management password. Keep advertised owner/device
   verification user-operated. Do not infer a Windows Hello exemption from a
   fresh install; it requires the advertised `windows-fresh-install` method and
   `not-required-for-fresh-install` verification. For other routes, use the full

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/jishudb-setup/references/setup-quickstart.md (reported line 124)May include surrounding context.

md
2. Read `/api/service/capabilities` from that verified endpoint without
   credentials or redirects. For `agentOnboarding.schemaVersion=1`,
   `supported=true` and `route=initial-consent` or `owner-consent`, use native
   OAuth without asking for a management password. Keep advertised owner/device
   verification user-operated. Do not infer a Windows Hello exemption from a
   fresh install; it requires the advertised `windows-fresh-install` method and
   `not-required-for-fresh-install` verification. For other routes, use the full

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
75% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · references/jishudb-setup/references/setup-quickstart.md (reported line 121)May include surrounding context.

md
refresh/reload action or an available authorized native UI to load it.
   Verify the named entry and endpoint in the client before mentioning Trust.
   If the list is still empty, finish the supported loading operation yourself
   or report that exact missing capability; never tell the user to trust an
   entry that is not there. A missing tool search
   alone does not prove a configuration cache problem. Do this work yourself
   when the controls are available, without asking the user to write JSON.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos-cnb.cjs (reported line 49)May include surrounding context.

js
if (matches.length !== 1) throw new Error(label + ' must exist exactly once');
  const asset = matches[0];
  assetDigest(asset, label);
  const expected = 'https://api.github.com/repos/x-aijishu/jishudb-desktop-releases/releases/assets/' + asset.id;
  if (asset.url !== expected) throw new Error(label + ' API URL is not canonical');
  return asset;
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos-cnb.cjs (reported line 309)May include surrounding context.

js
if (matches.length !== 1) throw new Error(label + ' must exist exactly once');
  const asset = matches[0];
  assetDigest(asset, label);
  const expected = 'https://api.github.com/repos/x-aijishu/jishudb-desktop-releases/releases/assets/' + asset.id;
  if (asset.url !== expected) throw new Error(label + ' API URL is not canonical');
  return asset;
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 206)May include surrounding context.

sh
if (matches.length !== 1) throw new Error(label + ' must exist exactly once');
  const asset = matches[0];
  assetDigest(asset, label);
  const expected = 'https://api.github.com/repos/x-aijishu/jishudb-desktop-releases/releases/assets/' + asset.id;
  if (asset.url !== expected) throw new Error(label + ' API URL is not canonical');
  return asset;
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 529)May include surrounding context.

sh
if (matches.length !== 1) throw new Error(label + ' must exist exactly once');
  const asset = matches[0];
  assetDigest(asset, label);
  const expected = 'https://api.github.com/repos/x-aijishu/jishudb-desktop-releases/releases/assets/' + asset.id;
  if (asset.url !== expected) throw new Error(label + ' API URL is not canonical');
  return asset;
}

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 934)May include surrounding context.

sh
[[ ! -e "$endpoint_path" ]] || fail "endpoint_conflict" "Desktop endpoint configuration appeared before launch"
  /usr/bin/printf '{\n  "localPort": %d,\n  "schemaVersion": %d\n}\n' "$port" "$ENDPOINT_CONFIG_SCHEMA" > "$endpoint_path" ||
    fail "endpoint_persistence_failed" "Desktop endpoint could not be persisted"
  /bin/chmod 600 "$endpoint_path"
}

run_plan() {

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 1005)May include surrounding context.

sh
[[ ! -e "$endpoint_path" ]] || fail "endpoint_conflict" "Desktop endpoint configuration appeared before launch"
  /usr/bin/printf '{\n  "localPort": %d,\n  "schemaVersion": %d\n}\n' "$port" "$ENDPOINT_CONFIG_SCHEMA" > "$endpoint_path" ||
    fail "endpoint_persistence_failed" "Desktop endpoint could not be persisted"
  /bin/chmod 600 "$endpoint_path"
}

run_plan() {

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 1263)May include surrounding context.

sh
validate_bundle_symlinks "${mount_point}/JishuDB.app" "mounted application bundle"
  [[ -z "$signed_team" ]] || verify_signed_artifact "${mount_point}/JishuDB.app" "$signed_team" app
  local bundle_id bundle_version runtime_binary
  bundle_id=$(/usr/libexec/PlistBuddy -c 'Print :CFBundleIdentifier' "${mount_point}/JishuDB.app/Contents/Info.plist")
  bundle_version=$(/usr/libexec/PlistBuddy -c 'Print :CFBundleShortVersionString' "${mount_point}/JishuDB.app/Contents/Info.plist")
  [[ "$bundle_id" == "com.aijishu.jishudb" && "$bundle_version" == "$version" ]] || fail "installer_content_invalid" "bundle identity or version does not match the plan"
  runtime_binary="${mount_point}/JishuDB.app/Contents/Resources/runtime/jishudb"

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 1264)May include surrounding context.

sh
validate_bundle_symlinks "${mount_point}/JishuDB.app" "mounted application bundle"
  [[ -z "$signed_team" ]] || verify_signed_artifact "${mount_point}/JishuDB.app" "$signed_team" app
  local bundle_id bundle_version runtime_binary
  bundle_id=$(/usr/libexec/PlistBuddy -c 'Print :CFBundleIdentifier' "${mount_point}/JishuDB.app/Contents/Info.plist")
  bundle_version=$(/usr/libexec/PlistBuddy -c 'Print :CFBundleShortVersionString' "${mount_point}/JishuDB.app/Contents/Info.plist")
  [[ "$bundle_id" == "com.aijishu.jishudb" && "$bundle_version" == "$version" ]] || fail "installer_content_invalid" "bundle identity or version does not match the plan"
  runtime_binary="${mount_point}/JishuDB.app/Contents/Resources/runtime/jishudb"