Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple remote LLM API example; it sends prompts to SkillBoss as its core function and does not install persistence or perform hidden local actions.
Install only if you are comfortable sending prompts and supplied text to SkillBoss and potentially routed model providers. Avoid submitting secrets, private customer data, regulated records, or proprietary material unless your organization approves that data flow.
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 instructs users to send prompts and text content to a third-party LLM API but does not warn that user input will leave the local environment and be processed remotely. This creates a real privacy and data-governance risk because users may unknowingly submit sensitive, proprietary, or regulated data to an external service.
The duplicated finding at this line captures the same risky behavior: the code serializes user-controlled prompt content into JSON and sends it to a third-party endpoint with an API key. Although not overtly malicious, this can expose confidential inputs and may violate organizational policies if users assume processing is local.
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 duplicated finding at this line captures the same risky behavior: the code serializes user-controlled prompt content into JSON and sends it to a third-party endpoint with an API key. Although not overtly malicious, this can expose confidential inputs and may violate organizational policies if users assume processing is local.
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 finding points to the explicit third-party endpoint used by the example function that sends prompts externally. Within this skill's context, remote inference is the core feature, which makes the behavior expected, but also makes undisclosed data exfiltration risk more significant because all user content is designed to leave the environment.
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,
This finding reflects the external endpoint in the curl example, again indicating remote transmission of user content to a third-party LLM hub. The skill context reduces suspicion of malicious intent but not the privacy risk, because users are encouraged to send arbitrary text for summarization and generation.
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"}'
This finding reflects the external endpoint in the curl example, again indicating remote transmission of user content to a third-party LLM hub. The skill context reduces suspicion of malicious intent but not the privacy risk, because users are encouraged to send arbitrary text for summarization and generation.
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.