ClawHub
Back to skill

Security audit

pi-ppt

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently generates presentations through PI's external API, with user-directed prompt and optional document upload behavior that is disclosed enough for a benign verdict.

Before installing, confirm you trust the PI service and the PIPPT_BASE_URL value you configure. Do not pass sensitive internal documents unless your organization allows sending them to PI for processing, and prefer an HTTPS official PI endpoint.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

Tainted flow: 'UPLOAD_FILE_URL' from os.getenv (line 19, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

This function uploads an arbitrary local file to a URL derived from environment configuration, and the code does not validate that the destination is an approved HTTPS PI endpoint. In a skill context, this is more dangerous because the feature is specifically designed to exfiltrate local document contents to an external service, so a misconfigured or attacker-influenced base URL could redirect sensitive files and API credentials off-platform.

Content

Scanner excerpt · scripts/generate_pi_ppt.py (reported line 88)May include surrounding context.

python
with open(file_path, "rb") as f:
        files = {"file": (file_name, f)}
        response = requests.post(UPLOAD_FILE_URL, data=data, files=files, timeout=30)
    if response.status_code != 200:
        print(
            f"[upload_file] request failed, status_code={response.status_code}, response_text={response.text}"

Tainted flow: 'GENERATION_URL' from os.getenv (line 17, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/generate_pi_ppt.py (reported line 126)May include surrounding context.

python
payload_with_sign = generate_signature_payload(app_id, app_secret, **payload)

    response = requests.post(GENERATION_URL, json=payload_with_sign, timeout=30)
    if response.status_code != 200:
        print(
            f"[create_document] request failed, status_code={response.status_code}, response_text={response.text}"

Tainted flow: 'GET_STATUS_URL' from os.getenv (line 18, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/generate_pi_ppt.py (reported line 149)May include surrounding context.

python
"resource_id": resource_id.strip(),
    }
    payload_with_sign = generate_signature_payload(app_id, app_secret, **payload)
    response = requests.post(GET_STATUS_URL, json=payload_with_sign, timeout=30)
    if response.status_code != 200:
        print(
            f"[get_status] request failed, status_code={response.status_code}, response_text={response.text}"

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill requires environment secrets and external network access but does not declare any explicit tool scope or permissions boundary. That omission can lead users or hosting platforms to underestimate what the skill can access, reducing transparency and increasing the chance of unintended secret exposure or outbound data transfer.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill supports uploading local documents to generate slides, but the description does not clearly warn that document contents will be transmitted to an external PI API service. This creates a real data-handling risk because users may provide sensitive internal files without informed consent, causing confidential information to leave the local environment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill uploads local files and sends prompt content to an external service without an explicit in-code warning, consent gate, or privacy notice at the point of transmission. In this skill's context, external transmission is the core function, which makes transparency especially important because users may provide sensitive documents expecting only local processing.

Content

No source excerpt is available for this finding.

Tainted flow: 'data' from requests.post (line 132, network input) → requests.post (network output)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/generate_pi_ppt.py (reported line 88)May include surrounding context.

python
with open(file_path, "rb") as f:
        files = {"file": (file_name, f)}
        response = requests.post(UPLOAD_FILE_URL, data=data, files=files, timeout=30)
    if response.status_code != 200:
        print(
            f"[upload_file] request failed, status_code={response.status_code}, response_text={response.text}"

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The code transmits user-provided presentation content and signed authentication fields to an external service. While this is intended functionality, it is still security-relevant because sensitive business data may leave the local environment, and the risk increases if the endpoint is not tightly controlled and transparently disclosed.

Content

Scanner excerpt · scripts/generate_pi_ppt.py (reported line 126)May include surrounding context.

python
payload_with_sign = generate_signature_payload(app_id, app_secret, **payload)

    response = requests.post(GENERATION_URL, json=payload_with_sign, timeout=30)
    if response.status_code != 200:
        print(
            f"[create_document] request failed, status_code={response.status_code}, response_text={response.text}"

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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 · scripts/generate_pi_ppt.py (reported line 149)May include surrounding context.

python
"resource_id": resource_id.strip(),
    }
    payload_with_sign = generate_signature_payload(app_id, app_secret, **payload)
    response = requests.post(GET_STATUS_URL, json=payload_with_sign, timeout=30)
    if response.status_code != 200:
        print(
            f"[get_status] request failed, status_code={response.status_code}, response_text={response.text}"

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The documentation states that the target language default is 'zh', which imposes a specific locale behavior unless the user overrides it. Under the language/locale policy, defaulting to a specific language without explicit opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The function signature sets language to "zh" by default, and the CLI also defaults to Chinese. This imposes a specific language choice unless the user notices and overrides it, which conflicts with the requirement to avoid forcing a locale without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.