Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward presentation-generation wrapper for a third-party API, with the main risk being that user-provided content is sent to SkillBoss/HeyBossAI.
Install only if you are comfortable sending prompts, drafts, pitch decks, reports, and related instructions to SkillBoss/HeyBossAI using your SKILLBOSS_API_KEY. Avoid submitting secrets, regulated data, or confidential business material unless that provider is approved for your use case.
The skill exposes shell-based execution examples and depends on a local script, but it does not declare any explicit tool scope or allowed-tools boundary. This weakens least-privilege controls and can let an agent invoke shell capabilities more broadly than the skill metadata suggests, increasing the chance of unintended command execution or misuse.
The skill encourages users to submit arbitrary presentation or document content to a third-party API, but it does not warn users that their content will leave the local environment. This creates a data leakage and consent problem, especially if users provide confidential business plans, reports, or proprietary text.
The skill explicitly transmits user-supplied content to an external endpoint at api.heybossai.com for generation. In this skill's context, external transmission is expected functionality, but it is still security-relevant because sensitive prompts, documents, or business content may be exposed to a third party and subject to external retention or processing.
POST https://api.heybossai.com/v1/pilot
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
set -euo pipefail
API_BASE="https://api.heybossai.com/v1"
# Check for API key
if [[ -z "${SKILLBOSS_API_KEY:-}" ]]; then
This function performs an authenticated POST to a remote API and includes user-controlled content in the JSON request body. While external transmission is expected for this skill's purpose, it is still a genuine security/privacy concern because potentially sensitive input is exported to a third party without safeguards such as consent prompts, redaction options, or destination validation controls.
# API request helper — routes all calls through SkillBoss /v1/pilot
api_pilot() {
local body="$1"
curl -s \
-X POST \
-H "Authorization: Bearer ${SKILLBOSS_API_KEY}" \
-H "Content-Type: application/json" \
The script transmits user-supplied content to a third-party service using curl, but it does not provide an explicit user-facing notice at execution time that prompt/content data will leave the local environment. In a skill that may be used with sensitive business drafts, pitch decks, or internal documents, this creates a real privacy and data-handling risk if users assume processing is local.
No suspicious patterns detected.