T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:10- Finding
Plaintext API Key Storage in Agent-Readable Documentation
- Content
View full analysis
- Remediation
View remediation
Security audit
Gamma Presentations
Security checks for vulnerabilities and agentic risk
Overview
The skill does what it claims, but it tells users to store and read a Gamma API key from a plaintext agent-readable file, which creates an avoidable credential exposure risk.
Install only if you are comfortable sending selected content to Gamma's API. Do not put the Gamma API key in TOOLS.md or any project document; use an environment variable or secret manager, and rotate any key that was already stored in plaintext.
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)
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 70% confidence
- Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- Content
md ## Setup 1. Get API key from https://developers.gamma.app 2. Store in environment: `export GAMMA_API_KEY=sk-gamma-xxx` Or add to TOOLS.md: `Gamma API Key: sk-gamma-xxx`
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill explicitly suggests placing the Gamma API key in TOOLS.md, a plaintext documentation file that may be read, indexed, or exposed during normal agent operation. This creates an avoidable credential exposure risk because secrets stored in local prompt-accessible files can leak to users, logs, or other tools.
- Content
Ssd 3
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
Advising operators to store the API key in a plaintext documentation file is a real secret-handling flaw in an agent skill context. Because agent systems often inspect local files as working context, the key could be unintentionally surfaced to the model, exfiltrated in outputs, or captured in logs and version control.
- Content
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
Generate Content
bash curl -X POST https://public-api.gamma.app/v1.0/generations \ -H "Content-Type: application/json" \ -H "X-API-KEY: $GAMMA_API_KEY" \ -d '{
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
Line L73 hard-codes a specific language in the natural-language example payload. This can violate language/locale policy when presented as the default behavior without telling users they can choose another language.
- Content
Static analysis
No suspicious patterns detected.