Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward web-search skill that sends user-provided search requests to the disclosed SkillBoss API and optionally saves results when the user asks it to.
Before installing, confirm you trust SkillBoss/HeyBoss with your search queries and API key. Do not include secrets, credentials, private customer data, or confidential internal project names in searches, and only use --output when you intend the results to remain on disk.
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.
def pilot(body: dict) -> dict:
r = requests.post(
f"{API_BASE}/pilot",
headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
json=body,
The skill clearly instructs users to send arbitrary search queries, filters, and related parameters to SkillBoss API Hub, but it does not explicitly warn that this data leaves the local environment and is transmitted to a third-party service. This can lead users or downstream agents to unintentionally disclose sensitive prompts, internal project names, personal data, or confidential research topics during web searches.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
from typing import List, Dict, Optional, Any
SKILLBOSS_API_KEY = os.environ.get("SKILLBOSS_API_KEY", "")
API_BASE = "https://api.heybossai.com/v1"
def pilot(body: dict) -> dict:
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
def pilot(body: dict) -> dict:
r = requests.post(
f"{API_BASE}/pilot",
headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
json=body,
User search queries and filters are transmitted to a third-party API, but the tool does not provide an explicit privacy or disclosure warning at runtime beyond implying use of SkillBoss in the help text. In agent or enterprise contexts, users may enter sensitive prompts, internal names, or investigative terms without realizing that data leaves the local environment.
The skill promotes saving search results to local files but does not clearly warn that retrieved content may be written to disk and persist beyond the current session. This can create unintended local data retention, especially if results contain sensitive research topics, user queries, or links/content that should not be stored on shared or monitored systems.
No suspicious patterns detected.