Security audit
Security checks for vulnerabilities and agentic risk
This is a small documentation-only skill for sending user prompts to a disclosed third-party LLM API, with no hidden local execution or persistence found.
Install only if you are comfortable sending prompts and inputs to SkillBoss-hosted infrastructure. Do not paste secrets, credentials, private customer data, regulated data, or internal documents unless your organization has approved that provider and its data-handling terms.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
---
name: gemini
description: LLM one-shot Q&A, summaries, and generation via SkillBoss API Hub.
homepage: https://api.SkillBoss.co/v1/pilot
metadata: {"clawdbot":{"emoji":"♊️","requires":{"env":["SkillBoss_API_KEY"]}}}
---
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
---
name: gemini
description: LLM one-shot Q&A, summaries, and generation via SkillBoss API Hub.
homepage: https://api.SkillBoss.co/v1/pilot
metadata: {"clawdbot":{"emoji":"♊️","requires":{"env":["SkillBoss_API_KEY"]}}}
---
The skill documentation instructs users to send arbitrary prompts to a third-party API but does not clearly warn that prompt contents may contain sensitive data and will be transmitted off-host. In an agent-skill context, this omission can cause users or downstream agents to unknowingly exfiltrate confidential text to an external service.
This example performs a live HTTPS POST to a third-party endpoint and includes user-supplied prompt content in the request body. In a skill meant for text generation, that behavior is expected, but it still creates a real data-exfiltration path if users paste sensitive content without understanding where it is sent.
SkillBoss_API_KEY = os.environ["SkillBoss_API_KEY"]
def ask(prompt: str, prefer: str = "balanced") -> str:
r = requests.post(
"https://api.SkillBoss.co/v1/pilot",
headers={"Authorization": f"Bearer {SkillBoss_API_KEY}", "Content-Type": "application/json"},
json={"type": "chat", "inputs": {"messages": [{"role": "user", "content": prompt}]}, "prefer": prefer},
This example performs a live HTTPS POST to a third-party endpoint and includes user-supplied prompt content in the request body. In a skill meant for text generation, that behavior is expected, but it still creates a real data-exfiltration path if users paste sensitive content without understanding where it is sent.
SkillBoss_API_KEY = os.environ["SkillBoss_API_KEY"]
def ask(prompt: str, prefer: str = "balanced") -> str:
r = requests.post(
"https://api.SkillBoss.co/v1/pilot",
headers={"Authorization": f"Bearer {SkillBoss_API_KEY}", "Content-Type": "application/json"},
json={"type": "chat", "inputs": {"messages": [{"role": "user", "content": prompt}]}, "prefer": prefer},
The curl example sends user content to the same external API endpoint using an authorization token, again establishing a direct off-system transmission channel. Because this is copy-pasteable documentation, users may transmit sensitive material without realizing they are sharing it with a third party.
Quick start (curl)
curl -s https://api.SkillBoss.co/v1/pilot \
-H "Authorization: Bearer $SkillBoss_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"chat","inputs":{"messages":[{"role":"user","content":"Summarize this text..."}]},"prefer":"balanced"}'
The curl example sends user content to the same external API endpoint using an authorization token, again establishing a direct off-system transmission channel. Because this is copy-pasteable documentation, users may transmit sensitive material without realizing they are sharing it with a third party.
Quick start (curl)
curl -s https://api.SkillBoss.co/v1/pilot \
-H "Authorization: Bearer $SkillBoss_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"chat","inputs":{"messages":[{"role":"user","content":"Summarize this text..."}]},"prefer":"balanced"}'
No suspicious patterns detected.