T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/seedream-generate.sh:4- Finding
Executable Credential Configuration Enables Shell Command Execution
- Content
View full analysis
- Remediation
View remediation
Security audit
Seedream 5 via BytePlus
Security checks for vulnerabilities and agentic risk
Overview
The skill does what it claims, but it handles credentials and output files in ways users should review before installing.
Install only if you are comfortable sending prompts to BytePlus Ark and using this script with a local API key. Avoid putting sensitive text in prompts, prefer passing SEEDREAM_API_KEY through the environment instead of relying on /root/.clawdbot/.env, and do not let untrusted input control the output filename.
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 (2)
T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/seedream-generate.sh:14- Finding
Caller-Controlled Output Path Allows Arbitrary File Overwrite
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 60% confidence
- Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- Content
sh #!/usr/bin/env bash set -euo pipefail if [[ -f /root/.clawdbot/.env ]]; then # shellcheck disable=SC1091 source /root/.clawdbot/.env fi
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 60% confidence
- Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- Content
sh #!/usr/bin/env bash set -euo pipefail if [[ -f /root/.clawdbot/.env ]]; then # shellcheck disable=SC1091 source /root/.clawdbot/.env fi
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
The skill invokes a shell script but does not declare any tool scope or allowed-tools boundary. That omission weakens execution controls and reviewability, increasing the chance the agent can run shell-based actions without explicit authorization or least-privilege constraints.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The trigger conditions are broad enough to fire on generic mentions of Seedream or BytePlus Ark, which can cause unintended invocation of a shell-backed skill. In practice, this may lead to accidental transmission of user prompts to an external service or unexpected local file downloads when the user did not explicitly request image generation.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill documentation does not clearly warn users that their prompts are sent to a third-party image-generation provider and that generated content is downloaded to local storage. This creates a privacy and data-handling risk, especially if users include sensitive, regulated, or proprietary information in prompts.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 70% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
sh PY ) RESP=$(curl -sS -X POST 'https://ark.ap-southeast.bytepluses.com/api/v3/images/generations' \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer ${SEEDREAM_API_KEY}" \ -d "$PAYLOAD")
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The script sends the user-supplied prompt and model parameters to a remote HTTP endpoint via curl, which is a network operation that transmits user data off-system. While the code checks for the API key and reports errors, it does not include a confirmation prompt, user-facing notice, or explanatory comment warning that prompt content will be sent to a third-party service.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
The script downloads the generated image and writes it to the specified output path, which is a file-write operation. Although echoing the resulting path provides some visibility after the fact, there is no prior warning, confirmation, or inline documentation telling users that a local file will be created automatically.
- Content