Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple documented example for sending prompts to SkillBoss's external LLM API, with no local install, persistence, or hidden execution behavior.
Install only if you are comfortable sending prompts and any included text to SkillBoss's API. Use a scoped SkillBoss_API_KEY where possible and avoid submitting secrets, confidential business data, personal data, or regulated content unless your policy allows that third-party processing.
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 explicitly sends user prompts to a third-party API but does not warn users that their prompts and any included data will be transmitted off-platform. This creates a real data exposure risk because users may unknowingly submit sensitive or regulated information to an external service.
The request includes prompt content and an API bearer token in an outbound call to a remote service. Although the token is placed in an authorization header rather than exposed in output, the skill still establishes a trust boundary crossing where user content is transmitted externally.
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 request includes prompt content and an API bearer token in an outbound call to a remote service. Although the token is placed in an authorization header rather than exposed in output, the skill still establishes a trust boundary crossing where user content is transmitted externally.
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 line contains the concrete remote endpoint used for API submission, confirming that prompt content is sent outside the local trust boundary to SkillBoss. In context, this is expected functionality, but it remains a real egress vector with privacy and compliance implications if users submit sensitive material.
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},
timeout=60,
The external URL in the curl example is part of an operational command that transmits message content to SkillBoss. Because the documentation lacks strong warnings, users may treat this as a harmless local example rather than a real external data transfer.
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 external URL in the curl example is part of an operational command that transmits message content to SkillBoss. Because the documentation lacks strong warnings, users may treat this as a harmless local example rather than a real external data transfer.
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.