Security audit
Security checks for vulnerabilities and agentic risk
This is a simple LLM API helper that clearly sends prompts to SkillBoss API Hub and does not install code, persist itself, or access local files beyond a user-provided API key.
Install only if you are comfortable sending prompts and included text to SkillBoss API Hub and potentially routed model providers. Do not include secrets, credentials, regulated personal data, or confidential business content unless your organization permits that use.
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.heybossai.com/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.heybossai.com/v1/pilot
metadata: {"clawdbot":{"emoji":"♊️","requires":{"env":["SKILLBOSS_API_KEY"]}}}
---
The skill explicitly encourages sending arbitrary user prompts and summaries to a third-party LLM API, but it does not warn users that their input will leave the local environment and be transmitted to an external service. This creates a real privacy and data-governance risk because users may paste secrets, proprietary data, or regulated information into the examples without understanding the transmission boundary.
The code sample shows authenticated external transmission of user content to a third-party endpoint, and the request body embeds the prompt directly without any warning, filtering, or minimization. That makes accidental exfiltration of sensitive data plausible, even though the code itself is not overtly malicious.
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
def ask(prompt: str, prefer: str = "balanced") -> str:
r = requests.post(
"https://api.heybossai.com/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 code sample shows authenticated external transmission of user content to a third-party endpoint, and the request body embeds the prompt directly without any warning, filtering, or minimization. That makes accidental exfiltration of sensitive data plausible, even though the code itself is not overtly malicious.
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
def ask(prompt: str, prefer: str = "balanced") -> str:
r = requests.post(
"https://api.heybossai.com/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 demonstrates sending prompt contents directly to an external API endpoint, again without any privacy warning or restrictions on what data may be included. Command-line examples are especially risky because users often copy-paste them verbatim, potentially sending internal text or sensitive notes to a remote provider.
Quick start (curl)
curl -s https://api.heybossai.com/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 demonstrates sending prompt contents directly to an external API endpoint, again without any privacy warning or restrictions on what data may be included. Command-line examples are especially risky because users often copy-paste them verbatim, potentially sending internal text or sensitive notes to a remote provider.
Quick start (curl)
curl -s https://api.heybossai.com/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.