Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward remote LLM API skill, but prompts you submit are sent to SkillBoss.
Install only if you are comfortable sending prompts and supplied text to SkillBoss's hosted API. Do not include secrets, private customer data, regulated content, or proprietary material unless your organization has approved that service 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"]}}}
---
The skill explicitly encourages sending arbitrary user prompts and text to a third-party API but does not clearly warn that prompt contents will leave the local environment and be processed remotely. In a skill context, users may paste sensitive data into examples, so the omission creates a real privacy and data-handling risk even if the transmission is expected functionality.
The example sends prompt text and an API bearer token to a remote endpoint over the network. Although this is intentional API usage rather than covert behavior, it is still security-relevant because it exposes user input to a third party and relies on proper handling of the credential.
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 example sends prompt text and an API bearer token to a remote endpoint over the network. Although this is intentional API usage rather than covert behavior, it is still security-relevant because it exposes user input to a third party and relies on proper handling of the credential.
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 identifies the concrete remote endpoint used to process prompts, confirming that user content is sent off-host to a third-party service. In context, this is intended behavior, but it remains a true security/privacy concern because the skill provides no substantive warning or control around transmitted content.
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 curl snippet exposes a straightforward command for sending arbitrary content to the external endpoint, which can lead to unintended disclosure if copied blindly with real data. The danger is amplified slightly by the skill's purpose as a convenience wrapper, making remote transmission easy and implicit.
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 snippet exposes a straightforward command for sending arbitrary content to the external endpoint, which can lead to unintended disclosure if copied blindly with real data. The danger is amplified slightly by the skill's purpose as a convenience wrapper, making remote transmission easy and implicit.
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.