T09 · Insecure Skill Coding Practices
Error
- Location
SKILL.md:258- Finding
Bearer Credentials and Sensitive Content May Be Sent to an Unrestricted Configurable Endpoint
- Content
View full analysis
- Remediation
View remediation
Security audit
Praesidia
Security checks for vulnerabilities and agentic risk
Overview
This is a plausible Praesidia integration, but it can send your API key and submitted content to a configurable service endpoint without enough safeguards.
Install only if you trust Praesidia and the configured API URL. Keep PRAESIDIA_API_URL on the official HTTPS endpoint unless you intentionally operate a trusted deployment, use the least-privileged API key available, and avoid submitting confidential or regulated content unless you are comfortable sending it to that service.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill description contains very broad trigger phrases such as general security, safety, guardrails, and agent-finding requests, which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that user prompts or sensitive context are routed into this skill and then sent to the Praesidia service, even when the user did not explicitly intend to use an external verification platform.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
Compliance: SOC2, GDPR Last verified: 2 days ago
Agent card: https://api.praesidia.ai/agents/chatbot-v2/agent-card
text ---
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
Compliance: SOC2, GDPR Last verified: 2 days ago
Agent card: https://api.praesidia.ai/agents/chatbot-v2/agent-card
text ---
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
Compliance: SOC2, GDPR Last verified: 2 days ago
Agent card: https://api.praesidia.ai/agents/chatbot-v2/agent-card
text ---
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill instructs the agent to submit agent identifiers, organization-scoped configuration, and especially arbitrary user-provided content to external guardrail and validation endpoints without a clear notice or consent step. This creates a real data-handling risk because users may paste sensitive prompts, regulated content, or proprietary data, assuming validation is local rather than transmitted to a third-party API.
- Content
Static analysis
No suspicious patterns detected.