T09 · Insecure Skill Coding Practices
Warning
- Location
examples/run.sh:18- Finding
API Key Exposed Through Command-Line Arguments
- Content
View full analysis
- Remediation
View remediation
Security audit
Product Description to Ad
Security checks for vulnerabilities and agentic risk
Overview
This skill coherently sends product descriptions to Revid to generate short ads, with no hidden persistence or unrelated local access found.
Install only if you are comfortable sending product copy, brand notes, and any provided media to Revid for processing. Avoid using confidential or regulated content unless approved, protect and rotate the Revid API key as needed, and prefer bounded polling and safer secret handling if adapting the example script for automation.
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
Note
- Location
examples/run.sh:21- Finding
Unbounded Status Polling and Missing Network Timeouts
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill sends user-supplied product descriptions and optional media to
www.revid.ai, but the user-facing description and usage guidance do not clearly warn that this content leaves the local system and is shared with a third-party service. This creates a data exposure risk if users paste confidential product plans, unpublished marketing copy, or proprietary images without informed consent.- 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 PAYLOAD=$(cat "$PAYLOAD_FILE") fi PID=$(curl -fsS https://www.revid.ai/api/public/v3/render \ -H "Content-Type: application/json" -H "key: $REVID_API_KEY" \ -d "$PAYLOAD" | jq -r .pid) echo "pid=$PID"
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The payload hard-codes
language: "en-US"for voice generation without indicating this to the user or allowing selection. While not a classic security flaw, it can cause unintended processing choices, misrepresentation of user intent, and accidental transmission of non-English content to a configuration the user did not approve.- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The configuration hard-codes the voice language to "en-US", which is a natural-language locale constraint. The file does not indicate that users can choose a different language or explicitly opt into this locale, so it may violate language/locale choice policy.
- Content
Static analysis
No suspicious patterns detected.